基于Caffe的猪肉新鲜度分级的设计与实现
|
摘要
为了提高猪肉新鲜度检测的实时性,提出了基于Caffe框架与ResNet残差神经网络的猪肉新鲜度分级的新方法。根据理化试验结果将猪肉的新鲜度分为7级,并在理化试验前拍摄对应的猪肉照片作为样本进行网络训练。在网络训练完成后分别用同源和异源样本图片对系统分级准确率进行验证,结果显示系统分级的准确率均达到95%以上,说明该系统能够很好地对猪肉新鲜度进行分级。与传统的理化试验检测新鲜度的方法相比,在保证了分级准确率较高的同时,检测过程简单、实时性高、无损,是一种更高效的猪肉新鲜度分级方法。
In order to improve the real-time detection of pork freshness, a new method of pork freshness classification was proposed based on Caffe framework and ResNet residual neural network. According to the results of pork physical and chemical experiments, the freshness of pork was divided into seven grades, and the corresponding pork photos were taken as samples for network training. After the network training, the classification accuracy of the system was validated by homologous and heterogeneous samples, respectively. The results showed that the classification accuracy of the system reached more than 95%, indicating that the system could classify the freshness of pork very well. Compared with the traditional physical and chemical methods, this method is simple, real-time and non-destructive, and it is a more efficient method for pork freshness classification.
In order to improve the real-time detection of pork freshness, a new method of pork freshness classification was proposed based on Caffe framework and ResNet residual neural network. According to the results of pork physical and chemical experiments, the freshness of pork was divided into seven grades, and the corresponding pork photos were taken as samples for network training. After the network training, the classification accuracy of the system was validated by homologous and heterogeneous samples, respectively. The results showed that the classification accuracy of the system reached more than 95%, indicating that the system could classify the freshness of pork very well. Compared with the traditional physical and chemical methods, this method is simple, real-time and non-destructive, and it is a more efficient method for pork freshness classification.
引文
[1] TOMOSHIGE S,OOST E,SHIMIZU A,et al.A conditional statistical shape model with integrated error estimation of the conditions:application to liver segmentation in non-contrast CT images[J].Medical Image Analysis,2014,18(1):130-143.
[2] RAJWADE A,RANGARAJAN A,BANERJEE A.Image denoising using the higher order singular value decomposition[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2012,35(4):849-862.
[3] 王彦闯,刘敬彪,蔡强,等.基于BP神经网络的猪肉新鲜度检测方法[J].计算机应用与软件,2011,28(9):82-84.
[4] 肖珂,段晓霞,高冠东.基于图像特征的猪肉新鲜度无损检测方法[J].河北农业大学学报,2012,35(4):111-113.
[5] 马世榜,徐杨,彭彦昆,等.基于光谱技术的支持向量机判别牛肉新鲜度[J].食品安全质量检测学报,2012,3(6):603-607.
[6] 兰韬,初侨,刘文,等.基于深度学习的牛肉大理石纹智能分级研究[J].食品安全质量检测学报,2018,9(5):1059-1064.
[7] JIAO J,MA H,QIAO Y,et al.Design of farm environmental monitoring system based on the internet of things[J].Advance Journal of Food Science & Technology,2014,6(3):368-373.
[8] 高雅,焦俊,孟珠李,等.基于HE和MSR的玉米病虫害图像预处理[J].合肥学院学报(综合版),2016,33(4):47-53.
[9] 孙永海,赵锡维,鲜于建川.基于计算机视觉的冷却牛肉新鲜度评价方法 [J].农业机械学报,2004,35(1):104-107.
[10] 郭培源.曲世海.猪肉新鲜度的智能检测方法[J].农业机械学报,2006,37(8):78- 81.
[11] 龚丁喜,曹长荣.基于卷积神经网络的植物叶片分类[J].计算机与现代化,2014(4):12-15
[12] 潘婧,钱建平,刘寿春,等.计算机视觉用于猪肉新鲜度检测的颜色特征优化选取[J].食品与发酵工业,2016,42(6):153-158.
[13] 魏正.基于Caffe平台深度学习的人脸识别研究与实现[D].西安:西安电子科技大学,2015.
[14] 欧先锋,向灿群,郭龙源,等.基于Caffe深度学习框架的车牌数字字符识别算法研究[J].四川大学学报(自然科学版),2017,54(5):971-977.
[15] 杨晓旭,高巍,顾颋.基于卷积神经网络Caffe框架的图像分类[J].电子技术与软件工程,2017(24):73-73.
[16] 焦俊,张水明,杜玉林,等.物联网技术在农田环境监测中的应用[J].中国农学通报,2014,30(20):290-295.
[17] 倪力,张政云,焦俊,等.基于可穿戴设备的山羊行为分类[J].山东农业大学学报(自然科学版),2018,49(2):235-239.
[18] 秦丰,刘东霞,孙炳达,等.基于深度学习和支持向量机的4种苜蓿叶部病害图像识别[J].中国农业大学学报,2017,22(7):123-133.
[19] 朱启兵,肖盼,黄敏,等.基于特征融合的猪肉新鲜度高光谱图像检测[J].食品与生物技术学报,2015,34(3):246-252.
[2] RAJWADE A,RANGARAJAN A,BANERJEE A.Image denoising using the higher order singular value decomposition[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2012,35(4):849-862.
[3] 王彦闯,刘敬彪,蔡强,等.基于BP神经网络的猪肉新鲜度检测方法[J].计算机应用与软件,2011,28(9):82-84.
[4] 肖珂,段晓霞,高冠东.基于图像特征的猪肉新鲜度无损检测方法[J].河北农业大学学报,2012,35(4):111-113.
[5] 马世榜,徐杨,彭彦昆,等.基于光谱技术的支持向量机判别牛肉新鲜度[J].食品安全质量检测学报,2012,3(6):603-607.
[6] 兰韬,初侨,刘文,等.基于深度学习的牛肉大理石纹智能分级研究[J].食品安全质量检测学报,2018,9(5):1059-1064.
[7] JIAO J,MA H,QIAO Y,et al.Design of farm environmental monitoring system based on the internet of things[J].Advance Journal of Food Science & Technology,2014,6(3):368-373.
[8] 高雅,焦俊,孟珠李,等.基于HE和MSR的玉米病虫害图像预处理[J].合肥学院学报(综合版),2016,33(4):47-53.
[9] 孙永海,赵锡维,鲜于建川.基于计算机视觉的冷却牛肉新鲜度评价方法 [J].农业机械学报,2004,35(1):104-107.
[10] 郭培源.曲世海.猪肉新鲜度的智能检测方法[J].农业机械学报,2006,37(8):78- 81.
[11] 龚丁喜,曹长荣.基于卷积神经网络的植物叶片分类[J].计算机与现代化,2014(4):12-15
[12] 潘婧,钱建平,刘寿春,等.计算机视觉用于猪肉新鲜度检测的颜色特征优化选取[J].食品与发酵工业,2016,42(6):153-158.
[13] 魏正.基于Caffe平台深度学习的人脸识别研究与实现[D].西安:西安电子科技大学,2015.
[14] 欧先锋,向灿群,郭龙源,等.基于Caffe深度学习框架的车牌数字字符识别算法研究[J].四川大学学报(自然科学版),2017,54(5):971-977.
[15] 杨晓旭,高巍,顾颋.基于卷积神经网络Caffe框架的图像分类[J].电子技术与软件工程,2017(24):73-73.
[16] 焦俊,张水明,杜玉林,等.物联网技术在农田环境监测中的应用[J].中国农学通报,2014,30(20):290-295.
[17] 倪力,张政云,焦俊,等.基于可穿戴设备的山羊行为分类[J].山东农业大学学报(自然科学版),2018,49(2):235-239.
[18] 秦丰,刘东霞,孙炳达,等.基于深度学习和支持向量机的4种苜蓿叶部病害图像识别[J].中国农业大学学报,2017,22(7):123-133.
[19] 朱启兵,肖盼,黄敏,等.基于特征融合的猪肉新鲜度高光谱图像检测[J].食品与生物技术学报,2015,34(3):246-252.