Classification of tough and tender beef by image texture analysis

Texture features of fresh-beef images were extracted and used to classify s teaks into tough and tender groups in terms of cooked-beef tenderness. Cros sbred steers varying in quality were processed in a commercial plant and tw o short loin steaks were sampled from each carcass. One sample was used for imaging and the other was broiled for sensory evaluation of tenderness by a trained panel. The samples were segregated into tough and tender groups a ccording to the sensory scores. A wavelet-based decomposition method was us ed to extract texture features of fresh-beef images. The texture feature da ta for 90 sample images were used to train and test sample calssifiers in a rotational leave-one-out scheme. A correct classification rate of 83.3% wa s obtained in cross validations. While texture features alone may not be su fficient to segregate beef products into many levels of tenderness, they ca n be significant members in a set of indicators that will lead to adequate tenderness prediction. (C) 2001 Elsevier Science Ltd. All rights reserved.