Image Recognition for Store Systems
Original Publication Date: 1985-Jan-01
Included in the Prior Art Database: 2005-Feb-18
This system provides a way for handling item identification in supermarkets and department stores in general. It is based on image recognition techniques to compare the video image of the item to be identified with a set of parameters and images which are stored in an image bank. The image recognition progresses in two steps: The prerecognition step provides the recognition of the contour of the object to be identified, principally giving the shape and the size of this item. The detailed recognition step focuses on the recognition of a specific spot of the image of the item, which is called the focused area. This area for each item is locatable with respect to the contour through appropriate coordinates stored with the reference image of the focused area in the image bank.