HYBRID IMAGE-PROCESSING FOR ROBUST EXTRACTION OF LEAN TISSUE ON BEEF CUT SURFACES

A hybrid image processing system which automatically distinguishes lea n tissues in the image of a complex beef cut surface and generates the lean tissue contour has been developed. Because of the inhomogeneous distribution and fuzzy pattern of fat and lean tissues on the beef cut , conventional image segmentation and contour generation algorithms su ffer from a heavy computing requirement, algorithm complexity and poor robustness. The proposed system utilizes an artificial neural network to enhance the robustness of processing. The system is composed of pr e-network, network, and post-network processing stages. At the pre-net work stage, gray level images of beef cuts were segmented and resized to be adequate to the network input. Features such as fat and bone wer e enhanced and the enhanced input image was converted to a grid patter n image, whose grid was formed as 4 x 4 pixel size. At the network sta ge, the normalized gray value of each grid image was taken as the netw ork input. The pre-trained network generated the grid image output of the isolated lean tissue. A sequence of post-network processing was co nducted to obtain the detailed contour of the lean tissue. A training scheme of the network and the separating performance were presented an d analyzed. The developed hybrid system showed the feasibility of the human-like robust object segmentation and contour generation for the c omplex, fuzzy and irregular image. (C) 1997 Elsevier Science B.V.