A seed imaging system for imaging seeds includes a seed transfer station configured to move seeds through the system. An imaging assembly includes a first camera mounted relative to the seed transfer station and configured to acquire images of the seeds as the seeds move through the system. A second camera is mounted relative to the seed transfer station and is configured to acquire images of the seeds as the seeds move through the system. The second camera has an imaging modality different from an imaging modality of the first camera. First and second cameras may be disposed above and below the seed transfer stations, such as a transparent belt.

Provided are a data collection method, a data collection system and a computer program for automatically collecting data in stages in classification. A data collection method is implemented by one or more processors connected to a sorting machine sorting articles to different sorting destinations. The method comprising: acquiring, by a processor, an identification code of an article from a reader provided on the sorting machine for identifying the article; acquiring, by a processor, image data of the article identified by the identification code from a camera that is attached so as to image the article after being read by the reader; storing, by a processor, the acquired image data so as to be associated with the acquired identification code.

Provided are a data collection method, a data collection system and a computer program for automatically collecting data in stages in classification. A data collection method is implemented by one or more processors connected to a sorting machine sorting articles to different sorting destinations. The method comprising: acquiring, by a processor, an identification code of an article from a reader provided on the sorting machine for identifying the article; acquiring, by a processor, image data of the article identified by the identification code from a camera that is attached so as to image the article after being read by the reader; storing, by a processor, the acquired image data so as to be associated with the acquired identification code.

Provided are a scrap determination system and method that can improve scrap determination techniques. A scrap determination system (1) comprises: a first scrap determination model (221) generated using teaching data including first learning images, and determines, based on a camera image, grade of scrap in the image and a ratio of the grade; a second scrap determination model (222) generated using teaching data including second learning images, and determines, based on the image, grade of scrap in the image and a ratio of the grade; a selection model (223) configured to determine which of the first scrap determination model (221) and the second scrap determination model (222) is to be used, based on the image; and an output section (24) configured to output information of each grade of scrap and a ratio of the grade determined based on the image using the model selected by the selection model (223).

Provided are a scrap determination system and method that can improve scrap determination techniques. A scrap determination system (1) comprises: a first scrap determination model (221) generated using teaching data including first learning images, and determines, based on a camera image, grade of scrap in the image and a ratio of the grade; a second scrap determination model (222) generated using teaching data including second learning images, and determines, based on the image, grade of scrap in the image and a ratio of the grade; a selection model (223) configured to determine which of the first scrap determination model (221) and the second scrap determination model (222) is to be used, based on the image; and an output section (24) configured to output information of each grade of scrap and a ratio of the grade determined based on the image using the model selected by the selection model (223).

A method for removing a piece good from a conveying means of a sorting system, wherein the sorting system includes the conveying means for conveying the piece good in a transport direction along a conveyor line, and wherein the conveying means is configured in such a way that a piece good arranged in a cell area on the conveying means is movable at right angles to the transport direction, includes the steps generating image data by means of a camera arranged on the conveyor line, wherein the image data represent at least the conveying means in one section of the conveyor line; by means of a controller, detecting a piece good not placed completely in the cell area on the conveying means on the basis of the image data generated; generating a blowoff command for a blowoff device arranged on the conveyor line, wherein the blowoff command is generated while considering a time of the generation of the image data, a conveying speed of the conveying means, and an arrangement of the camera, the conveyor line and the blowoff device relative to one another; and by means of the blowoff device, blowing off the piece good not placed completely in the cell area on the conveying means on the basis of the blowoff command.

A singulation conveyor for conveying and separating piece goods, in particular packages and/or consignments, along at least one transport track bearing the piece goods items is described, wherein in the transport track, in some sections, finger elements adjustable between a lower setting and an upper setting are provided, and wherein the free ends of the finger elements in the upper setting are arranged in an upper position above an adjoining region of the transport track in such a way as to manipulate the motional direction and/or the motional speed of respectively individual piece goods items independently of other piece goods items.

Disclosed are methods and systems for spectral imaging of soybean samples to accurately and non-destructively measure the amount of sucrosyl-oligosaccharide in the soybean samples. Populations containing modified and unmodified soybean seeds and having varying amounts of sucrosyl-oligosaccharides, oil or protein can be sorted and separated and further used in soybean processing or breeding.

A method and system for training a machine learning model configured to perform characterization of components in a material stream with a plurality of unknown components. A training reward associated with each unknown component within the plurality of unknown components in the material stream is determined, based on which at least one unknown component is physically isolated from the material stream by means of a separator unit, wherein the separator unit is configured to move the selected unknown component to a separate accessible compartment. The isolated at least one unknown component is analyzed for determining the ground truth label thereof, wherein the determined ground truth is used for training an incremental version of the machine learning model.

A method of sorting chips divided from a plate-shaped workpiece into acceptable chips and defective chips includes an ultrasonic vibration applying step of applying ultrasonic vibrations to chips, a fracture confirming step of confirming whether the chips have been fractured in the ultrasonic vibration applying step or not, and a sorting step of sorting those chips which have been confirmed as not fractured in the fracture confirming step as acceptable chips. The ultrasonic vibrations applied to the chips in the ultrasonic vibration applying step are set to values that do not cause chips to be fractured if the chips are free of minute fractures and cause chips to be fractured if the chips contain minute fractures.