Included are a chute arranged in an inclined manner to allow sorting targets to flow downward, optical detection means for detecting the sorting targets at a detection position, and ejector means for sorting and removing the sorting targets based on a result of detection of the optical detection means. The chute is provided with an optical detection slit in a direction orthogonal to a flow-down direction of the sorting targets, a slit width of the optical detection slit is adjustable, and the optical detection means images the sorting targets flowing downward on the chute with the imaging means at a position where the optical detection slit is provided as the detection position.

Provided is a method for processing electronic and electrical device component scrap, which can accurately and efficiently sort electronic and electrical device component scrap. The method for processing electronic and electrical device component scrap includes a separation step of separating non-metal objects 1b or metal objects 1a.sub.1, 1a.sub.2 from electronic and electrical device component scrap 1 containing the metal objects 1a.sub.1, 1a.sub.2 and the non-metal objects 1b using a sorter 10 comprising a metal sensor 2, a color camera 3, an air valve 4, and a conveyor 5, wherein a fixed distance is provided between the metal objects 1a.sub.1, 1a.sub.2 adjacent to each other so as to prevent the non-metal objects 1b between the metal objects 1a.sub.1, 1a.sub.2 from being erroneously detected, when detecting the metal objects 1a.sub.1, 1a.sub.2 in the electronic and electrical device component scrap 1 by the metal sensor 2.

A bulk sorting system for sorting objects in bulk is provided. The bulk sorting system includes: at least one radiation source arranged to radiate the objects, at least one optical sensor arranged to capture reflected radiation of the objects and acquire the reflected radiation as multi- or hyperspectral data; a processing circuit configured to analyze the reflected radiation of the objects by inputting the multi- or hyperspectral data into a convolutional neural network (CNN) with at least two convolutional layers in order to either detect and classify the objects in the multi- or hyperspectral data and/or semantically segment the multi- or hyperspectral data; and a mechanical sorter configured to sort the objects according to their classification and/or segmentation using the analysis of the processing circuit such that different overlapping and/or stacked objects are separated or treated as a single group of objects.

An apparatus for classifying materials utilizing a vision system, which may implement an artificial intelligence system in order to identify or classify each of the materials, which may then be separated from a heap in a scrap yard into separate groups, such as other heaps, based on such an identification or classification. The artificial intelligence system may utilize a neural network, and be previously trained to recognize and classify certain types of materials.

A system for processing scrap material that includes a variable-power electromagnetic drum separator wherein shredded scrap material is placed in free fall at a position proximate the electromagnetic drum separator. A first fraction of the scrap material is attracted to the electromagnetic drum separator and is carried under the rotational axis of the electromagnetic drum separator thereby separating the first fraction of material from a second fraction of the material which continues to free fall and wherein the first fraction is a low-copper ferrous material with the second fraction having a higher non-ferrous content than the first fraction. A magnetic drum separator may be positioned upstream of the variable-power electromagnetic drum separator and be used to separate non-ferrous materials. The variable-power electromagnetic drum separator may be adjusted so that the second fraction includes some ferrous material. A robotic picker may be used to remove undesirable materials from the second fraction.

A machine vision system for automatically identifying and inspecting objects is disclosed, including composable vision-based recognition modules and a decision algorithm to perform the final determination on object type and quality. This vision system has been used to develop a Projectile Identification System and an Automated Tactical Ammunition Classification System. The technology can be used to create numerous other inspection and automated identification systems.

Embodiments relate to a crop harvesting apparatus configured to garner or harvest crops from plants via vacuum suction and sort the garnered crops via a quick-switching gate system. A vacuum source generates the vacuum suction for the apparatus so that crops are garnered (or plucked) from the plant via suction through an end-effector, which are then transferred to a crop sorter by way of tubing that has a smooth inner surface. The crop sorter utilizes a gate system that exploits vacuum suction from the vacuum source and gravity to quickly and effectively sort the garnered crops into a hopper and a rejection bin.

A system for sorting seeds based on their resistance to a stress is disclosed. Batches of purified seeds sorted using the system are also disclosed.

Methods and apparatuses for detecting characteristics of a card include a method for identifying a card containing foil, the foil detection method comprising converting an image file depicting a card into a hue, saturation, value (“HSV”) colour space, applying a value mask to exclude a group of pixels from analysis that do not form an intensified brightness area, and comparing the number of remaining pixels against a threshold to determine whether the card contains foil. In another aspect, a method for assigning a condition grading to a card comprises converting an image file depicting a diffusely illuminated card into an HSV colour space, isolating a uniform portion of the converted image file, applying a value mask to the converted image file to exclude pixels forming an undamaged portion of the card, and comparing the number of remaining pixels to a plurality of grading thresholds to assign a condition grading.

A method and apparatus are provided for sorting items to form groups at respective sort destinations. A scanning station evaluates one or more characteristics of each item fed into the apparatus. The items are loaded onto one of a plurality of independently controlled delivery vehicles. The delivery vehicles are individually driven to sort destinations. Once at the appropriate sort destination, the delivery vehicle ejects the item to the sort destination and returns to receive another item to be delivered. A re-induction conveyor may be provided for receiving select items from the vehicles and conveying the items back to the input station for re-processing. Additionally, a controller is provided to control the movement of the vehicles based on a characteristic each item being delivered by each vehicle. When an item to be manually sorted is encountered, a visual alert aligned with a selected destination is activated until manual transfer is confirmed.