基于深度学习的牛肉大理石纹智能分级研究

目的开发客观、准确、无损的基于深度学习的牛肉大理石纹智能化分级技术。方法将深度学习的图像识别方法应用于牛肉大理石纹的特征提取和分类上,并进行相应的调试和学习。结果通过计算机调试和学习,评级正确率分别达到84.2%(一级)、89.4%(二级)、81.9%(三级)、84.1%(四级)、82.6%(五级)。各级牛肉的识别率均在80%以上,识别时间都在1 s以内,达到了预期目标。结论将深度学习的图像识别方法应用于牛肉大理石纹的特征提取和分类上,评级准确率非常高,且随着图片数据库样本数的不断增多,其识别的准确度将不断提高,可进行大量推广使用。

Research on intelligent grading of beef marbling based on deep learning

Objective Beef quality grading is very important for the beef industry. The abundance and the degree of dispersion of beef marbling is the most important index for beef grading. This paper intends to develop an objective, accurate and nondestructive intelligent grading method of beef marbling in order to overcome the drawbacks of artificial rating. Methods The image recognition method based on deep learning algorithm was used for feature extraction and classification of beef marbling in this article, and the corresponding debugging and learning was carries out. Results The accuracy rate of beef marbling grading reached to 84.2% for first level, 89.4% for the second level, 81.9% for the third level, 84.1% for the forth level and 82.6% for the fifth level, respectively, through the computer debugging and learning. The recognition rates of beef at all levels were above 80%, and the recognition time were all within 1s. It was better than a 1-2 years primary judger. The software reached the expected goal. Conclusion With the increasing number of samples in the picture database, the accuracy of its recognition will be improved continuously. The image recognition method based on deep learning algorithm was used for feature extraction and classification of beef marbling in this study, the accuracy of this method is good, and can be widely used.