Texture image analysis: application to the classification of bovine muscles from meat slice images

Image texture is analyzed to provide a series of features for the classific ation of several sets of images. Images of meat slices are processed to cla ssify various samples of bovine muscle as a function of three factors: anim al age, muscle and castration. The different images present a particular te xture that is a global representation of the connective tissue. The aim of texture analysis is to extract specific features for each kind of meat. The meat slices available for this study came from 19 animals, including 10 ca strated animals. Their ages were 4 months (10 animals), 12 months (5 animal s) and 16 months (4 animals). The same three muscles were studied for each animal. The texture analysis was carried out on digitized images using the first- and second-order statistics of the gray levels and morphological par ameters, for the characterization of the marbling. Two classification metho ds were implemented: the method of the k-nearest neighbors and a method bas ed on neural networks. Both methods give comparable results and lead to sat isfactory classification of the samples in relation to the three variation factors. The correlation of the textural features with chemical and mechani cal parameters measured on the meat samples is also examined. Regression ex periments show that textural features have potential to indicate meat chara cteristics. (C) 1999 Society of Photo-Optical Instrumentation Engineers. [S 0091-3286(99)01111-3].