Determination of Meat Quality by Image Processing and Neural Network Techniques
Kazuhiko Shiranita, Kenichiro Hayashi and Akifumi Otsubo
Applied Electronics Division, Industrial Technology Center of Saga Prefecture, Japan
Received:February 9, 2000Accepted:April 11, 2000Published:August 20, 2000
Keywords:Meat Quality, Image Processing, Neural Network, Multiple Regression Analysis, Beef Marbling Score, Grading System
We study the implementation of a meat-quality grading system, using the concept of the marbling score, and image processing, neural network techniques and multiple regression analysis. The marbling score is a measure of the distribution density of fat in the rib-eye region. We identify five features used for grading meat images. For the evaluation of the five features, we propose a method of image binarization using a three-layer neural network developed based on inputs given by a professional grader and a system of meat-quality grading based on the evaluation of three of five features with multiple regression analysis. Experimental results show that the system is effective.
Cite this article as:K. Shiranita, K. Hayashi, and A. Otsubo, “Determination of Meat Quality by Image Processing and Neural Network Techniques,” J. Robot. Mechatron., Vol.12 No.4, pp. 474-479, 2000.Data files:
Copyright© 2000 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.