基于改进YOLOv3模型的软包装食品自动识别方法  

Automatic recognition method for soft packaged food based on improved YOLOv3 model

作　　者：张志凯[1] 韩红章[2] 赵雪芊 李忠[4] ZHANG Zhi-kai;HAN Hong-zhang;ZHAO Xue-qian;LI Zhong(Jiangsu Suzhou Silk Secondary Professional School,Suzhou,Jiangsu 215228,China;Jiangsu University of Technology,Changzhou,Jiangsu 213000,China;Nanjing University,Nanjing,Jiangsu 210023,China;Changzhou Liu Guojun Branch,Jiangsu United Vocational and Technical College,Changzhou,Jiangsu 213000,China)

机构地区：[1]江苏省苏州丝绸中等专业学校,江苏苏州215228 [2]江苏理工学院,江苏常州213000 [3]南京大学,江苏南京210023 [4]江苏联合职业技术学院常州刘国钧分院,江苏常州213000

出　　处：《食品与机械》2023年第5期95-100,共6页Food and Machinery

基　　金：江苏省自然科学基金项目(编号:21JS23879023)。

摘　　要：目的:解决现有包装食品自动识别方法存在的识别精度差、效率低等问题。方法:基于软包装食品自动识别系统,提出一种改进的YOLOv3模型用于软包装食品的自动识别。将Kmeans++算法引入模型中解决小目标不敏感问题,将Mish激活函数引入模型中提高识别的准确性,将注意力机制Senet引入模型中提高特征提取能力。通过试验分析了该识别模型的性能,验证了模型的优越性。结果:与常规识别方法相比,所提方法能更准确、高效地实现软包装食品的自动识别,识别准确率为95.40%,识别效率为23.80帧/s,满足包装食品识别的需要。结论:通过对现有食品识别模型的优化,可以有效提高识别模型的性能。Objective:To solve the problems of poor recognition accuracy and low efficiency of existing automatic recognition methods for packaged food.Methods:Based on the automatic identification system of packaged food,an improved YOLOv3 model was proposed for the automatic identification of soft packaged food.The Kmeans++algorithm was introduced into the model to solve the problem of small target insensitivity,the Mish activation function was introduced into the model to improve the accuracy of recognition,and the attention mechanism Senet was introduced into the model to improve the ability of feature extraction.The performance of the recognition model was analyzed through experiments,and the superiority of the model was verified.Results:Compared with the conventional recognition methods,the proposed method can more accurately and efficiently realize the automatic recognition of flexible packaging food,the recognition accuracy rate was 95.40%,and the recognition efficiency was 23.80 f/s,which meets the needs of packaging food recognition.Conclusion:By optimizing the existing food recognition model,the performance of the recognition model can be effectively improved.

关 键 词：软包装食品 自动识别 YOLOv3模型 Kmeans++算法 Mish激活函数 注意力机制Senet 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TS207.3[自动化与计算机技术—计算机科学与技术]