Methods and apparatus for inspecting and sorting

A method of sorting, comprising:

• providing a product stream formed of individual objects of interest, each having at least one feature aspect which can be detected;
• providing a plurality of detection devices, which when actuated, each generate a device signal, and positioning each of the plurality of detection devices at a known position relative to the product stream, and the known position of each of the plurality of detection devices being different from the known position of every other of the plurality of detection devices, and wherein the known position of each of the plurality of detection devices provides a known, and different from every other of the plurality of detection devices, perspective field of view of the product stream, and wherein a portion of each known, perspective field of view of each of the plurality of detection devices, is shared with at least one other known, perspective field of view of another of the plurality of detection devices;
• generating multiple images of the product stream using the device signals, each image having different angular views of the respective objects of interest having the detectable feature aspect, and assigning an identifier signal to each image;
• classifying each feature aspect of each of the objects of interest as being either a parent or a child feature;
• identifying a complementary region of the images of the respective objects of interest by analyzing at least some of the previously classified parent or child features classified in some of the multiplicity of images;
• fusing the complementary regions of the images using the assigned identifier signals so as to form a resulting aggregated region representation of each of the objects of interest;
• and
• sorting the respective objects of interest based, at least in part, upon the aggregated region representation which is formed.

A method of inspecting and sorting, the method comprising:

• providing a product stream formed of a plurality of individual objects of interest, each individual object of interest having at least one feature aspect which can be detected;
• providing a plurality of detection devices, which when actuated, each generate a device signal, and positioning each of the plurality of detection devices at a known position relative to the product stream, and the known position of each of the plurality of detection devices being different from the known position of every other of the plurality of detection devices, and wherein the known position of each of the plurality of detection devices provides a known, and different from every other of the plurality of detection devices, perspective field of view of the product stream, and wherein a portion of each known, perspective field of view of each of the plurality of detection devices, is shared with at least one other known, perspective field of view of another of the plurality of detection devices;
• using the device signals, generating multiple images of the product stream formed of the plurality of individual objects of interest, each of the generated multiple images having a different angular view of the product stream and the respective individual objects of interest having at least one detectable feature aspect, and assigning an identifier signal to each of the generated multiple images;
• identifying and classifying each detectable feature aspect of each of the individual objects of interest in the generated multiple images formed from the device signals as a parent feature or a child feature;
• analyzing at least some of the identified and classified parent features or the identified and classified child features identified in the generated multiple images to identify a complementary region which comprises a portion of at least one of the plurality of known and different perspective fields of view that is shared with at least one other of the plurality of known and different perspective fields of view of the generated multiple images;
• selectively actuating the respective plurality of detection devices, and generating the multiple different perspective images from the generated device signals and assigning the identifier signal to each of the multiple different perspective images which are formed by the plurality of device signals received from the selectively actuated detection devices;
• fusing image features together using the identified complementary regions of the generated multiple images, and using the assigned identifier signals, to form a resulting aggregated region representation of each individual object of interest;
• and
• sorting the respective individual objects of interest in the product stream based, at least in part, upon the aggregated region representation.