Abstract Beef images were pretreated based on the hue component of the HSV color space, and an improved watershed algorithm was proposed to separate the rib-eye and beef marbling region from the images. Meanwhile, the correlations of characteristics parameters from U.S., Chinese and Japanese standard grading graphs were analyzed. Five characteristic parameters were selected for beef marbling distribution. A new automatic grading method based on improved watershed method and Hopfield network was proposed, and the results indicated that the accuracy of this method was 87.23%.
Received: 20 October 2011
Published: 07 January 2013