{"id":12699,"date":"2026-10-09T15:00:23","date_gmt":"2026-10-09T13:00:23","guid":{"rendered":"https:\/\/www.optimum-sorting.com\/gruene-bohnen-praeziser-sortieren-mit-ki-und-deep-learning\/"},"modified":"2026-10-21T16:01:17","modified_gmt":"2026-10-21T14:01:17","slug":"deep-learning-gruene-bohnen","status":"publish","type":"post","link":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/","title":{"rendered":"Gr\u00fcne Bohnen pr\u00e4ziser sortieren mit KI und Deep Learning"},"content":{"rendered":"[vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][vc_column_text css=““ text_direction=“default“]\n

Die Qualit\u00e4tskontrolle von Gem\u00fcse hat in den vergangenen Jahren gro\u00dfe Fortschritte gemacht. Moderne Kamera- und Lasersysteme pr\u00fcfen und sortieren selbst gro\u00dfe Produktmengen heute mit hoher Pr\u00e4zision. Doch sobald Fremdmaterial oder Defekte dem eigentlichen Produkt optisch stark \u00e4hneln, sto\u00dfen herk\u00f6mmliche Technologien h\u00e4ufig an ihre Grenzen. Genau hier er\u00f6ffnen K\u00fcnstliche Intelligenz und Deep Learning<\/strong> neue M\u00f6glichkeiten.<\/em><\/em><\/p>\n

Auf dieser Grundlage entwickelte Optimum Sorting ein neues Sortiermodell namens A-EYE<\/strong>. Die Technologie kann unter anderem bei der Verarbeitung von Spinat und Gr\u00fcnen Bohnen eingesetzt werden. Defekte, die bislang kaum oder gar nicht erkannt werden konnten, lassen sich heute zuverl\u00e4ssig aussortieren. Wie A-EYE die Grenzen herk\u00f6mmlicher Sortiertechnologien erweitert und welche Ergebnisse dabei in der Praxis erzielt werden, erfahren Sie in den folgenden Beispielen.<\/em><\/p>\n[\/vc_column_text][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][nectar_animated_title heading_tag=“h4″ style=“color-strip-reveal“ color=“Extra-Color-1″ text=“Wichtige Erkenntnisse:“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][nectar_icon_list animate=“true“ color=“Extra-Color-1″ direction=“horizontal“ columns=“1″ icon_size=“large“ icon_style=“border“][nectar_icon_list_item icon_type=“numerical“ text_full_html=“html“ title=“List Item“ id=“1792573725612-1″ tab_id=“1792573725612-6″]\n

Erkennen Sie mit A-EYE Defekte, die dem Produkt optisch stark \u00e4hneln und sich nur schwer unterscheiden lassen.<\/h6>\n[\/nectar_icon_list_item][nectar_icon_list_item icon_type=“numerical“ text_full_html=“html“ title=“List Item“ id=“1792573725630-5″ tab_id=“1792573725630-8″]\n
Entdecken Sie, wie wir erfolgreiche Tests mit Gr\u00fcnen Bohnen (Erkennung von Stielenden und St\u00e4ngeln) durchgef\u00fchrt haben.<\/h6>\n[\/nectar_icon_list_item][nectar_icon_list_item icon_type=“numerical“ text_full_html=“html“ title=“List Item“ id=“1792573725637-7″ tab_id=“1792573725637-0″]\n
Beschleunigen Sie die Einf\u00fchrung neuer Sortieranwendungen mit Modellen, die sich in kurzer Zeit entwickeln lassen.<\/h6>\n[\/nectar_icon_list_item][\/nectar_icon_list][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][vc_column_text css=““ text_direction=“default“]\n

Wie verbessert Deep Learning Ihre Sortierung?<\/h3>\n

Bei herk\u00f6mmlichen Sortiertechnologien legt ein Bediener oder Softwareentwickler im Voraus fest, welche Produkteigenschaften analysiert werden sollen. Dazu z\u00e4hlen beispielsweise Farbunterschiede, Formabweichungen oder bestimmte Gr\u00f6\u00dfenmerkmale. F\u00fcr viele Anwendungen funktioniert dieser Ansatz sehr gut. Schwieriger wird es jedoch, wenn unerw\u00fcnschte Bestandteile dem Produkt selbst optisch stark \u00e4hneln. Wie soll eine Kamera ohne zus\u00e4tzliche Hilfsmittel den Unterschied zwischen Gut- und Schlechtprodukt erkennen?<\/p>\n

Das A-EYE-Modell von Optimum Sorting verfolgt einen anderen Ansatz. Grundlage daf\u00fcr ist Deep Learning, eine spezielle Form der K\u00fcnstlichen Intelligenz, bei der Computermodelle aus gro\u00dfen Mengen an Daten und Beispielen lernen<\/strong>. Der zugrunde liegende Prozess \u00e4hnelt dabei der Art und Weise, wie Menschen Produkte wahrnehmen und beurteilen. Ein erfahrener Qualit\u00e4tsmitarbeiter achtet nicht nur auf ein einzelnes Merkmal, sondern erkennt ein Objekt als Ganzes. A-EYE folgt derselben Logik. Anstatt jede Eigenschaft isoliert zu bewerten, analysiert das Modell Formen, Strukturen, Proportionen und visuelle Muster im Gesamtzusammenhang.<\/p>\n

Mit Deep Learning als Grundlage eignet sich A-EYE besonders f\u00fcr komplexe Sortieraufgaben in der Gem\u00fcseverarbeitung<\/a><\/strong><\/span>. Die Technologie erg\u00e4nzt bestehende Sortiersysteme ideal, etwa f\u00fcr die Erkennung von Verf\u00e4rbungen oder anderen klar sichtbaren Defekten. Wie A-EYE in der Praxis eingesetzt wird und welche Ergebnisse sich bei Spinat und Gr\u00fcnen Bohnen erzielen lassen, zeigen die folgenden Beispiele.<\/p>\n[\/vc_column_text][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][image_with_animation image_url=“12648″ image_size=“custom“ animation_type=“entrance“ animation=“Fade In From Bottom“ animation_easing=“default“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=“center“ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“ custom_image_size=“850px“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ top_margin=“2%“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][nectar_animated_title heading_tag=“h3″ style=“color-strip-reveal“ color=“Accent-Color“ text=“Praxisbeispiel 1: GR\u00dcNE BOHNEN“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][vc_column_text css=““ text_direction=“default“]\n

Stielenden detektieren<\/h3>\n\n

Bei der Verarbeitung von Gr\u00fcnen Bohnen bietet unser A-EYE-Modell klare Vorteile. Eine konkrete Anwendung ist die Erkennung von Stielenden<\/strong>. F\u00fcr herk\u00f6mmliche Sortiersysteme sehen das Stielende und die Bohnenspitze oft sehr \u00e4hnlich aus, sodass eine zuverl\u00e4ssige Unterscheidung nicht immer einfach ist.<\/p>\n

F\u00fcr herk\u00f6mmliche Sortiersysteme sind diese Unterschiede kaum zu erkennen. Bohnen mit Stielenden geh\u00f6ren jedoch nicht ins Endprodukt. Durch das Training mit Tausenden von Praxisbildern lernt das Modell, diese feinen Unterschiede zu erkennen, und kann deutlich pr\u00e4ziser bestimmen, welche Bohnen ausgesondert werden m\u00fcssen.<\/p>\n[\/vc_column_text][\/vc_column][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ top_margin=“4%“ constrain_group_2=“yes“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][nectar_flip_box image_url_1=“12442″ text_color=“dark“ icon_color=“accent-color“ image_url_2=“12467″ text_color_2=“dark“ h_text_align=“center“ v_text_align=“center“ image_loading=“default“ flip_direction=“vertical-to-top“][\/nectar_flip_box][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][vc_column_text css=““ text_direction=“default“]\n

St\u00e4ngeln detektieren<\/h3>\n\n

Dar\u00fcber hinaus unterst\u00fctzt A-EYE bei der Erkennung von St\u00e4ngeln, Zweigen und anderen unerw\u00fcnschten Pflanzenresten<\/strong>, die w\u00e4hrend der Ernte in den Produktstrom gelangen.<\/p>\n

Da diese Pflanzenreste den Bohnen in Farbe und Form oft sehr \u00e4hnlich sind, sto\u00dfen herk\u00f6mmliche Erkennungsmethoden schnell an ihre Grenzen. Mit Deep Learning bewertet A-EYE das Objekt als Ganzes und kann dadurch deutlich zuverl\u00e4ssiger zwischen Produkt und unerw\u00fcnschten Bestandteilen unterscheiden. Selbst bei \u00fcberlappenden Objekten oder unterschiedlichen Positionen auf dem F\u00f6rderband trifft das Modell eine pr\u00e4zise und zuverl\u00e4ssige Entscheidung.<\/p>\n[\/vc_column_text][\/vc_column][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ top_margin=“4%“ constrain_group_2=“yes“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][nectar_flip_box image_url_1=“12447″ text_color=“dark“ icon_color=“accent-color“ image_url_2=“12457″ text_color_2=“dark“ h_text_align=“center“ v_text_align=“center“ image_loading=“default“ flip_direction=“vertical-to-top“][\/nectar_flip_box][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][vc_column_text css=““ text_direction=“default“]\n

Portulak detektieren<\/h3>\n\n

Eine dritte und besonders interessante Anwendung ist die Erkennung von Portulak<\/strong> (Portulaca oleracea). Aufgrund strengerer Anforderungen im Pflanzenschutz und des r\u00fcckl\u00e4ufigen Einsatzes von Herbiziden breitet sich diese Pflanze auf manchen Anbaufl\u00e4chen zunehmend aus und w\u00e4chst zwischen den Bohnenkulturen. Nach der Ernte und Verarbeitung weist Portulak oft starke optische \u00c4hnlichkeiten mit Gr\u00fcnen Bohnen auf, wodurch eine zuverl\u00e4ssige Unterscheidung zur Herausforderung wird.<\/p>\n

Dank Deep Learning kann das Sortiersystem auch diese feinen Unterschiede zuverl\u00e4ssig erkennen. W\u00e4hrend das Vorkommen von Portulak fr\u00fcher zur Aussortierung ganzer Chargen f\u00fchren konnte, k\u00f6nnen Gem\u00fcseverarbeiter heute deutlich gezielter sortieren. Das reduziert Produktverluste, erh\u00f6ht die Produktausbeute und tr\u00e4gt dazu bei, einen gr\u00f6\u00dferen Anteil des Rohmaterials f\u00fcr den Verzehr nutzbar zu machen.<\/p>\n[\/vc_column_text][\/vc_column][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ top_margin=“6%“ constrain_group_2=“yes“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][nectar_flip_box image_url_1=“12459″ text_color=“dark“ icon_color=“accent-color“ image_url_2=“12461″ text_color_2=“dark“ h_text_align=“center“ v_text_align=“center“ image_loading=“default“ flip_direction=“vertical-to-top“][\/nectar_flip_box][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ enable_animation=“true“ animation=“fade-in-from-bottom“ animation_easing=“default“ bg_image_animation=“ro-reveal-from-top“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][divider line_type=“No Line“][nectar_gradient_text heading_tag=“h2″ color=“extra-color-gradient-1″ gradient_direction=“horizontal“ text=“„Deep Learning steigerte die Erkennungsrate von Stielenden in Gr\u00fcnen Bohnen von rund 70% auf 97%„“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ top_margin=“2%“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][nectar_animated_title heading_tag=“h3″ style=“color-strip-reveal“ color=“Accent-Color“ text=“Praxisbeispiel 2: SPINAT“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ bottom_margin=“-1%“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][vc_column_text css=““ text_direction=“default“]\n

Unkraut detektieren<\/h3>\n\n

Eine der gr\u00f6\u00dften Herausforderungen bei der Verarbeitung von Spinat besteht darin, unerw\u00fcnschte Bestandteile zu erkennen, die vom Produkt selbst kaum zu unterscheiden sind. Gr\u00e4ser und bestimmte Unkrautarten<\/strong>, darunter Disteln und Brennnesseln, weisen h\u00e4ufig dieselbe Farbe, eine \u00e4hnliche Struktur und teilweise sogar eine vergleichbare Blattform wie Spinat auf.<\/p>\n

Genau hier zeigt Deep Learning seine St\u00e4rken. W\u00e4hrend herk\u00f6mmliche Kamerasysteme Schwierigkeiten haben, solche feinen Unterschiede zuverl\u00e4ssig und konstant zu erkennen, kann ein trainiertes KI-Modell lernen, welche Merkmale typisch f\u00fcr Spinat sind und welche auf unerw\u00fcnschtes Material hinweisen. Dadurch lassen sich heute Defekte und Fremdmaterial erkennen, die fr\u00fcher h\u00e4ufig unentdeckt blieben.<\/p>\n[\/vc_column_text][\/vc_column][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][carousel script=“flickity“ flickity_formatting=“default“ desktop_cols_flickity=“1″ desktop_small_cols_flickity=“1″ tablet_cols_flickity=“1″ phone_cols_flickity=“1″ flickity_controls=“next_prev_arrows_overlaid“ color=“default“ flickity_overflow=“hidden“ flickity_wrap_around=“wrap“ flickity_spacing=“default“ flickity_column_vertical_alignment=“default“ column_padding=“0″ flickity_element_spacing=“default“ border_radius=“none“][item simple_slider_bg_image_position=“default“ simple_slider_overlay_strength=“0.3″ simple_slider_bg_image_loading=“default“ id=“1792573726178-4″ tab_id=“1792573726179-5″ title=“Artikel“][image_with_animation image_url=“12426″ image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][\/item][item simple_slider_bg_image_position=“default“ simple_slider_overlay_strength=“0.3″ simple_slider_bg_image_loading=“default“ id=“1792573726212-7″ tab_id=“1792573726213-3″ title=“Artikel“][image_with_animation image_url=“12450″ image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][\/item][item simple_slider_bg_image_position=“default“ simple_slider_overlay_strength=“0.3″ simple_slider_bg_image_loading=“default“ title=“Sectie“ id=“1792573726238-4″ tab_id=“1792573726238-3″][image_with_animation image_url=“12452″ image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][\/item][item simple_slider_bg_image_position=“default“ simple_slider_overlay_strength=“0.3″ simple_slider_bg_image_loading=“default“ id=“1792573726261-4″ tab_id=“1792573726261-2″ title=“Artikel“][image_with_animation image_url=“12451″ image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][\/item][item simple_slider_bg_image_position=“default“ simple_slider_overlay_strength=“0.3″ simple_slider_bg_image_loading=“default“ title=“Sectie“ id=“1792573726286-5″ tab_id=“1792573726286-0″][image_with_animation image_url=“12453″ image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][\/item][\/carousel][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][vc_column_text css=““ text_direction=“default“]\n

Schnellere Entwicklung von Trainingsmodellen<\/h3>\n\n

Bevor ein Deep-Learning-Modell Defekte erkennen kann, muss es mit gro\u00dfen Mengen an Praxisdaten trainiert werden. Dank moderner Cloud-Plattformen und neuer Trainingsmethoden l\u00e4uft dieser Prozess heute deutlich schneller ab als noch vor einigen Jahren<\/strong>. Dar\u00fcber hinaus k\u00f6nnen neue KI-Modelle auf dem Wissen bereits bestehender Anwendungen aufbauen, wodurch sich Entwicklungszeiten erheblich verk\u00fcrzen.<\/p>\n

Noch vor wenigen Jahren dauerte die Entwicklung eines neuen Modells oft mehrere Monate. Heute kann eine vergleichbare Anwendung bereits nach wenigen Wochen produktiv eingesetzt werden. So l\u00e4sst sich beispielsweise ein Modell f\u00fcr eine neue Bohnensorte auf Erkenntnisse aus bestehenden Anwendungen f\u00fcr Gr\u00fcne Bohnen aufbauen. Auch bereits trainierte Modelle k\u00f6nnen mit neuen Praxisdaten h\u00e4ufig innerhalb weniger Stunden weiter verbessert werden. Der Trainingsprozess gliedert sich in drei Schritte:<\/p>\n[\/vc_column_text][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ constrain_group_5=“yes“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“ gradient_type=“default“ shape_type=““][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ enable_animation=“true“ animation=“fade-in-from-bottom“ animation_easing=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][vc_row_inner equal_height=“yes“ column_margin=“none“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ text_align=“left“ row_position=“default“ row_position_tablet=“inherit“ row_position_phone=“inherit“ overflow=“visible“ pointer_events=“all“][vc_column_inner top_padding_desktop=“10%“ constrain_group_100=“yes“ bottom_padding_desktop=“10%“ left_padding_desktop=“10%“ constrain_group_101=“yes“ right_padding_desktop=“10%“ top_padding_tablet=“64″ bottom_padding_tablet=“64″ left_padding_tablet=“5%“ constrain_group_103=“yes“ right_padding_tablet=“5%“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color=“#323a04″ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ font_color=“#ffffff“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ overflow=“visible“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/3″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_color=“#efefef“ column_border_style=“solid“ column_padding_type=“advanced“ gradient_type=“default“][nectar_icon icon_family=“iconsmind“ icon_style=“default“ icon_color_type=“color_scheme“ icon_color=“white“ icon_padding=“0px“ pointer_events=“all“ icon_iconsmind=“iconsmind-Finger-DragFourSides“][vc_column_text css=““ text_direction=“default“]\n

Bilder erfassen und kennzeichnen<\/h4>\n[\/vc_column_text][divider line_type=“No Line“ custom_height=“25px“]
\n
    \n
  • Tausende Bilder von einwandfreien Produkten und Defekten werden erfasst und gekennzeichnet. So lernt das Modell, welche Objekte erw\u00fcnscht sind und welche aussortiert werden m\u00fcssen.<\/li>\n<\/ul>\n <\/div>[\/vc_column_inner][vc_column_inner top_padding_desktop=“10%“ constrain_group_100=“yes“ bottom_padding_desktop=“10%“ left_padding_desktop=“10%“ constrain_group_101=“yes“ right_padding_desktop=“10%“ top_padding_tablet=“64″ constrain_group_102=“yes“ bottom_padding_tablet=“64″ left_padding_tablet=“5%“ constrain_group_103=“yes“ right_padding_tablet=“5%“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color=“#99a200″ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ font_color=“#ffffff“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ overflow=“visible“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/3″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_color=“#efefef“ column_border_style=“solid“ column_padding_type=“advanced“ gradient_type=“default“][nectar_icon icon_family=“iconsmind“ icon_style=“default“ icon_color_type=“color_scheme“ icon_color=“white“ icon_padding=“0px“ pointer_events=“all“ icon_iconsmind=“iconsmind-Dumbbell“][vc_column_text css=““ text_direction=“default“]\n

    Das Modell trai\u00adnieren und testen<\/h4>\n[\/vc_column_text][divider line_type=“No Line“ custom_height=“25px“]
    \n
      \n
    • Anhand dieser Beispiele lernt das System, Muster zu erkennen. Anschlie\u00dfend wird es mit neuen Bildern getestet, die es zuvor noch nicht gesehen hat, um seine Zuverl\u00e4ssigkeit zu \u00fcberpr\u00fcfen.<\/li>\n<\/ul>\n <\/div>[\/vc_column_inner][vc_column_inner top_padding_desktop=“10%“ constrain_group_100=“yes“ bottom_padding_desktop=“10%“ left_padding_desktop=“10%“ constrain_group_101=“yes“ right_padding_desktop=“10%“ top_padding_tablet=“64″ bottom_padding_tablet=“64″ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color=“#efefef“ background_color_opacity=“1″ background_color_hover=“#efefef“ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ overflow=“visible“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/3″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_color=“#efefef“ column_border_style=“solid“ column_padding_type=“advanced“ gradient_type=“default“][nectar_icon icon_family=“iconsmind“ icon_style=“default“ icon_color_type=“color_scheme“ icon_color=“Accent-Color“ icon_padding=“0px“ pointer_events=“all“ icon_iconsmind=“iconsmind-Camera-4″][vc_column_text css=““ text_direction=“default“]\n

      Sortierung in der Produktion<\/h4>\n[\/vc_column_text][divider line_type=“No Line“ custom_height=“25px“]
      \n
        \n
      • Nach der Validierung wird das Modell in die Sortiermaschine integriert. W\u00e4hrend der Produktion analysiert es jedes Produkt innerhalb von Millisekunden und entscheidet automatisch, ob es im Produktstrom verbleibt oder ausgeschleust wird.<\/li>\n<\/ul>\n <\/div>[\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][vc_column_text css=““ text_direction=“default“]\n

        Weniger Produktverluste, mehr Qualit\u00e4t und h\u00f6here Kapazit\u00e4ten<\/h3>\n\n

        Mit A-EYE erweitert Optimum Sorting die M\u00f6glichkeiten moderner Sortiertechnologien deutlich. Durch die Kombination von KI und Deep Learning mit Kamerainspektion und k\u00fcnftig auch mit Lasern und anderen Sensoren lassen sich Defekte erkennen, die bislang nur schwer oder sogar gar nicht automatisch detektiert werden konnten.<\/p>\n

        Damit er\u00f6ffnen sich neue Anwendungsm\u00f6glichkeiten f\u00fcr Aufgaben, die mit herk\u00f6mmlicher Bildverarbeitung oft nur schwer zu l\u00f6sen sind. Dazu z\u00e4hlen beispielsweise die Erkennung von Unkraut in Spinat, die Unterscheidung von Portulak und Gr\u00fcnen Bohnen sowie die Detektion von Stielenden und anderen unerw\u00fcnschten Pflanzenresten. Verarbeiter gewinnen dadurch mehr Kontrolle \u00fcber die Produktqualit\u00e4t, steigern die Ausbeute und reduzieren Produktverluste.<\/p>\n

        Die Vorteile von A-EYE gehen weit \u00fcber eine verbesserte Defekterkennung hinaus. Praxistests bei bestehenden Kunden belegen, dass die Technologie auch die Sortierkapazit\u00e4t steigern kann<\/strong>. Bei einem Verarbeiter von Gr\u00fcnen Bohnen erh\u00f6hte sich die Kapazit\u00e4t nach der Einf\u00fchrung von A-EYE um +25 %, von rund 8 auf 10 Tonnen pro Stunde. Selbst bei sich \u00fcberlappenden Produkten auf dem F\u00f6rderband erkannte und bewertete das System die einzelnen Objekte zuverl\u00e4ssig. Wo herk\u00f6mmliche Algorithmen unter solchen Bedingungen an Genauigkeit verlieren, sorgt A-EYE weiterhin f\u00fcr eine hohe Sortierpr\u00e4zision. Mehr Produkt verarbeiten, ohne Abstriche bei der Qualit\u00e4t zu machen. Ist das nicht genau das Ziel jedes Verarbeiters?<\/strong><\/p>\n[\/vc_column_text][divider line_type=“No Line“ custom_height=“2px“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][nectar_single_testimonial testimonial_style=“small_modern“ image=“12500″ text_color=“#99a200″ color=“Default“ quote=“F\u00fcr uns steht beim Deep Learning nicht die K\u00fcnstliche Intelligenz selbst im Mittelpunkt, sondern die L\u00f6sung von Herausforderungen, die sich bislang nur schwer automatisieren lie\u00dfen. Seit 2019 bauen wir Schritt f\u00fcr Schritt Know-how in diesem Bereich auf. Gemeinsam mit spezialisierten Partnern haben wir insbesondere im vergangenen Jahr erhebliche Fortschritte bei Anwendungen f\u00fcr die Obst-, Gem\u00fcse- und Lebensmittelverarbeitung erzielt. Heute verf\u00fcgen wir \u00fcber das Wissen und die Werkzeuge, um Sortieraufgaben zu l\u00f6sen, die noch vor wenigen Jahren als nicht realisierbar galten. Mit der Einf\u00fchrung unseres A-EYE-Modells m\u00f6chten wir neue Ma\u00dfst\u00e4be daf\u00fcr setzen, was Verarbeiter von moderner Sortiertechnologie erwarten k\u00f6nnen.“ name=“Jan De Jonghe“ subtitle=“CTO Optimum Sorting“][divider line_type=“No Line“ custom_height=“3px“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][vc_video link=“https:\/\/www.youtube.com\/watch?v=PTF7LHyy9KU“ css=““][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/1″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“ column_padding_type=“default“ gradient_type=“default“][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][divider line_type=“No Line“][vc_column_text css=““ text_direction=“default“]\n

        Interesse an einer kostenlosen Demo?<\/span><\/h3>\n

        Kontaktieren Sie das Vertriebsteam von Optimum Sorting und lassen Sie Ihre Produkte ausf\u00fchrlich in einem unserer Demo-Center weltweit testen.
        \nErleben Sie selbst, welchen Mehrwert unsere Maschinen f\u00fcr Ihr Unternehmen bieten k\u00f6nnen![\/vc_column_text][nectar_btn size=“large“ button_style=“regular“ button_color_2=“Accent-Color“ icon_family=“default_arrow“ text=“Starten Sie hier Ihre Anfrage“ url=“https:\/\/www.optimum-sorting.com\/de\/demo\/“ css_animation=“fadeInUp“][divider line_type=“No Line“][divider line_type=“Full Width Line“ line_thickness=“2″ divider_color=“default“ animate=“yes“][\/vc_column][\/vc_row][vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][image_with_animation image_size=“full“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“none“ alignment=““ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“][vc_column_text css=““ text_direction=“default“]\n

        Was ist A-EYE?<\/h3>\n\n

        Mit A-EYE pr\u00e4sentiert Optimum Sorting eine innovative Sortiertechnologie, die Deep Learning nutzt, um komplexe Defekte zu erkennen. Im Gegensatz zu herk\u00f6mmlichen Systemen lernt A-EYE aus Praxisdaten und kann dadurch selbst feine Unterschiede erkennen, die bislang h\u00e4ufig unentdeckt blieben. So lassen sich Anwendungen automatisieren, die noch vor wenigen Jahren nur schwer realisierbar waren. Das Ergebnis: weniger Produktverluste und eine h\u00f6here Endproduktqualit\u00e4t.<\/p>\n[\/vc_column_text][nectar_btn size=“large“ button_style=“regular“ button_color_2=“Accent-Color“ icon_family=“default_arrow“ text=“Mehr \u00fcber A-EYE erfahren“ url=“https:\/\/www.optimum-sorting.com\/de\/demo\/“ css_animation=“none“][\/vc_column][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“ column_padding_position=“all“ column_element_direction_desktop=“default“ column_element_spacing=“default“ desktop_text_alignment=“default“ tablet_text_alignment=“default“ phone_text_alignment=“default“ background_color_opacity=“1″ background_hover_color_opacity=“1″ column_backdrop_filter=“none“ column_shadow=“none“ column_border_radius=“none“ column_link_target=“_self“ column_position=“default“ gradient_direction=“left_to_right“ overlay_strength=“0.3″ width=“1\/2″ tablet_width_inherit=“default“ animation_type=“default“ bg_image_animation=“none“ border_type=“simple“ column_border_width=“none“ column_border_style=“solid“][image_with_animation image_url=“12601″ image_size=“medium_large“ animation_type=“entrance“ animation=“None“ animation_movement_type=“transform_y“ hover_animation=“zoom“ alignment=“center“ border_radius=“none“ box_shadow=“none“ image_loading=“default“ max_width=“100%“ max_width_mobile=“default“ margin_top=“14%“][\/vc_column][\/vc_row]\n","protected":false},"excerpt":{"rendered":"

        [vc_row type=“in_container“ full_screen_row_position=“middle“ column_margin=“default“ column_direction=“default“ column_direction_tablet=“default“ column_direction_phone=“default“ scene_position=“center“ text_color=“dark“ text_align=“left“ row_border_radius=“none“ row_border_radius_applies=“bg“ overflow=“visible“ overlay_strength=“0.3″ gradient_direction=“left_to_right“ shape_divider_position=“bottom“ bg_image_animation=“none“][vc_column column_padding=“no-extra-padding“ column_padding_tablet=“inherit“ column_padding_phone=“inherit“…<\/p>\n","protected":false},"author":3,"featured_media":12696,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[141],"tags":[135],"class_list":["post-12699","post","type-post","status-publish","format-standard","has-post-thumbnail","category-gemuese","tag-novus"],"yoast_head":"\nDeep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting<\/title>\n<meta name=\"description\" content=\"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Deep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting\" \/>\n<meta property=\"og:description\" content=\"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\" \/>\n<meta property=\"og:site_name\" content=\"Optimum Sorting\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/optimumsorting\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-09T13:00:23+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-21T14:01:17+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1043\" \/>\n\t<meta property=\"og:image:height\" content=\"1044\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Christophe Jansen\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christophe Jansen\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"11\u00a0Minuten\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\"},\"author\":{\"name\":\"Christophe Jansen\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/c7a37d556817c0553f3a0a524ac76c2d\"},\"headline\":\"Gr\u00fcne Bohnen pr\u00e4ziser sortieren mit KI und Deep Learning\",\"datePublished\":\"2026-10-09T13:00:23+00:00\",\"dateModified\":\"2026-10-21T14:01:17+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\"},\"wordCount\":7249,\"publisher\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg\",\"keywords\":[\"Novus\"],\"articleSection\":[\"Gem\u00fcse\"],\"inLanguage\":\"de\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\",\"url\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\",\"name\":\"Deep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting\",\"isPartOf\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg\",\"datePublished\":\"2026-10-09T13:00:23+00:00\",\"dateModified\":\"2026-10-21T14:01:17+00:00\",\"description\":\"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#breadcrumb\"},\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage\",\"url\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg\",\"contentUrl\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg\",\"width\":1043,\"height\":1044,\"caption\":\"Deep Learning in der Gem\u00fcsesortierung\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.optimum-sorting.com\/de\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Gr\u00fcne Bohnen pr\u00e4ziser sortieren mit KI und Deep Learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#website\",\"url\":\"https:\/\/www.optimum-sorting.com\/de\/\",\"name\":\"Optimum Sorting\",\"description\":\"Your worldwide expert in optical sorting solutions for food and non-food products\",\"publisher\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.optimum-sorting.com\/de\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"de\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#organization\",\"name\":\"Optimum Sorting\",\"url\":\"https:\/\/www.optimum-sorting.com\/de\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2025\/07\/Optimum_Logo.png\",\"contentUrl\":\"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2025\/07\/Optimum_Logo.png\",\"width\":303,\"height\":75,\"caption\":\"Optimum Sorting\"},\"image\":{\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/optimumsorting\/\",\"https:\/\/www.instagram.com\/optimumsorting\/\",\"https:\/\/www.youtube.com\/@optimumsorting\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/c7a37d556817c0553f3a0a524ac76c2d\",\"name\":\"Christophe Jansen\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/c6fd64885ec07c354824772e2976af023d5327aadeba1290bd74a9b6e5059343?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/c6fd64885ec07c354824772e2976af023d5327aadeba1290bd74a9b6e5059343?s=96&d=mm&r=g\",\"caption\":\"Christophe Jansen\"},\"url\":\"https:\/\/www.optimum-sorting.com\/de\/author\/christophe\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Deep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting","description":"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/","og_locale":"de_DE","og_type":"article","og_title":"Deep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting","og_description":"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.","og_url":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/","og_site_name":"Optimum Sorting","article_publisher":"https:\/\/www.facebook.com\/optimumsorting\/","article_published_time":"2026-10-09T13:00:23+00:00","article_modified_time":"2026-10-21T14:01:17+00:00","og_image":[{"width":1043,"height":1044,"url":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg","type":"image\/jpeg"}],"author":"Christophe Jansen","twitter_card":"summary_large_image","twitter_misc":{"Verfasst von":"Christophe Jansen","Gesch\u00e4tzte Lesezeit":"11\u00a0Minuten"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#article","isPartOf":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/"},"author":{"name":"Christophe Jansen","@id":"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/c7a37d556817c0553f3a0a524ac76c2d"},"headline":"Gr\u00fcne Bohnen pr\u00e4ziser sortieren mit KI und Deep Learning","datePublished":"2026-10-09T13:00:23+00:00","dateModified":"2026-10-21T14:01:17+00:00","mainEntityOfPage":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/"},"wordCount":7249,"publisher":{"@id":"https:\/\/www.optimum-sorting.com\/de\/#organization"},"image":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage"},"thumbnailUrl":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg","keywords":["Novus"],"articleSection":["Gem\u00fcse"],"inLanguage":"de"},{"@type":"WebPage","@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/","url":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/","name":"Deep Learning f\u00fcr Gr\u00fcne Bohnen | Optimum Sorting","isPartOf":{"@id":"https:\/\/www.optimum-sorting.com\/de\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage"},"image":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage"},"thumbnailUrl":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg","datePublished":"2026-10-09T13:00:23+00:00","dateModified":"2026-10-21T14:01:17+00:00","description":"Komplexe Defekte und Fremdmaterial in Gr\u00fcnen Bohnen besser erkennen? Erfahren Sie, wie KI und Deep Learning den Unterschied machen.","breadcrumb":{"@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#breadcrumb"},"inLanguage":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/"]}]},{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#primaryimage","url":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg","contentUrl":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2026\/10\/Deep-Learning_01.jpg","width":1043,"height":1044,"caption":"Deep Learning in der Gem\u00fcsesortierung"},{"@type":"BreadcrumbList","@id":"https:\/\/www.optimum-sorting.com\/de\/deep-learning-gruene-bohnen\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.optimum-sorting.com\/de\/"},{"@type":"ListItem","position":2,"name":"Gr\u00fcne Bohnen pr\u00e4ziser sortieren mit KI und Deep Learning"}]},{"@type":"WebSite","@id":"https:\/\/www.optimum-sorting.com\/de\/#website","url":"https:\/\/www.optimum-sorting.com\/de\/","name":"Optimum Sorting","description":"Your worldwide expert in optical sorting solutions for food and non-food products","publisher":{"@id":"https:\/\/www.optimum-sorting.com\/de\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.optimum-sorting.com\/de\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"de"},{"@type":"Organization","@id":"https:\/\/www.optimum-sorting.com\/de\/#organization","name":"Optimum Sorting","url":"https:\/\/www.optimum-sorting.com\/de\/","logo":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/logo\/image\/","url":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2025\/07\/Optimum_Logo.png","contentUrl":"https:\/\/www.optimum-sorting.com\/wp-content\/uploads\/2025\/07\/Optimum_Logo.png","width":303,"height":75,"caption":"Optimum Sorting"},"image":{"@id":"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/optimumsorting\/","https:\/\/www.instagram.com\/optimumsorting\/","https:\/\/www.youtube.com\/@optimumsorting"]},{"@type":"Person","@id":"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/c7a37d556817c0553f3a0a524ac76c2d","name":"Christophe Jansen","image":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.optimum-sorting.com\/de\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/c6fd64885ec07c354824772e2976af023d5327aadeba1290bd74a9b6e5059343?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c6fd64885ec07c354824772e2976af023d5327aadeba1290bd74a9b6e5059343?s=96&d=mm&r=g","caption":"Christophe Jansen"},"url":"https:\/\/www.optimum-sorting.com\/de\/author\/christophe\/"}]}},"_links":{"self":[{"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/posts\/12699","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/comments?post=12699"}],"version-history":[{"count":8,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/posts\/12699\/revisions"}],"predecessor-version":[{"id":12722,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/posts\/12699\/revisions\/12722"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/media\/12696"}],"wp:attachment":[{"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/media?parent=12699"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/categories?post=12699"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.optimum-sorting.com\/de\/wp-json\/wp\/v2\/tags?post=12699"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}