Grading meat quality by texture analysis

We describe a method of determining meat quality using the concepts of "marbling score" and texture analysis. The marbling score is a measure of the distribution density of fat in the rib-eye region. In this system, we consider the marbling of meat as a texture pattern. We use a gray level cooccurrence matrix as a texture feature and make standard texture-feature vectors for each grade using it. The grade of an unevaluated image is determined by comparing the texture-feature vector of this unevaluated image with the standard texture-feature vectors. Experimental results show that the system is effective.