Image processing algorithm for cheese shred evaluation

Abstract A robust and efficient algorithm called the X – Y sweep method is proposed for image segmentation. In this method a visual scene is swept in X -direction and Y -direction and two sets of run-length codes are generated. According to the width conditions and spatial relations with the neighbor run-length codes, the run-length codes are grouped as segments. A joint is formed by collecting the pixels that cannot be swept through in X -direction or Y -direction. The occluded shred shaped objects can be recovered by merging the neighbor blocks based on the local, semi-local and global descriptions. The topological sorting method is used to find the best match. The X – Y sweep method can work correctly to all the shred-shaped objects. An accuracy of 99% was obtained for pre-cut touching and overlapping straight copper wires. The tests with “in situ” cheese shreds (i.e., touching and overlapping as poured from its packaging) was about 95% accurate in estimating shred lengths. Uniformity of shreds can be objectively determined from the shred length distribution histogram. Two cheese shred quality indices, degree of free-flowing and degree of matting are also proposed based on X – Y sweep measurements.