食品科学 ›› 2013, Vol. 34 ›› Issue (1): 140-145.

• 基础研究 • 上一篇    下一篇

基于改进分水岭算法及Hopfield神经网络的牛肉大理石纹等级评级方法

孟祥艳   

  1. 西安工业大学电子信息工程学院
  • 收稿日期:2011-10-20 修回日期:2012-12-08 出版日期:2013-01-15 发布日期:2013-01-07
  • 通讯作者: 孟祥艳 E-mail:wulizu@126.com

Grading Method for Beef Marbling Based on Improved Watershed Algorithm and Hopfield Network

Xiang-Yan MENG   

  • Received:2011-10-20 Revised:2012-12-08 Online:2013-01-15 Published:2013-01-07
  • Contact: Xiang-Yan MENG E-mail:wulizu@126.com

摘要: 在HSV颜色空间H分量图像上进行分割预处理,结合改进分水岭算法对牛眼肌与大理石花纹区域进行精确分割,对中国、日本及美国的大理石纹的标准等级图的特征参数作相关性分析,优选出5个表征大理石纹分布的特征参数,提出一种基于图像处理及Hopfield神经网络的自动评级方法,结果表明,对大理石花纹分级准确率达到87.23%。

关键词: 农产品品质检测及机器视觉, 牛肉大理石纹, Hopfield神经网络, 分水岭算法, 评级

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%.

Key words: quality inspection and machine vision of farm products, beef marbling, Hopfield network, watershed algorithm, grading

中图分类号: