基于X射线的盒装水饺异物自动检测与分类
|
摘要
针对盒装水饺中的异物严重危害消费者身心健康,以及传统金属检测机只能检测金属、检测结果无法直观可视的现状,提出使用X射线成像技术和图像处理技术对水饺中的金属钢球、细铁丝、螺钉、石头和玻璃5种异物进行自动检测与分类方法.首先提取图像的LBP, HOG, Gabor纹理特征构建特征向量,使用支持向量机对异物水饺图像进行识别;在图像分割阶段,提出一种附加偏移量的最大熵算法与线性递减权重的粒子群算法结合的阈值分割算法,把图像目标区域的熵附加一个偏移函数,将图像总熵作为粒子群算法的适应度函数来获取图像的最佳分割阈值,实现对异物水饺图像的分割;在异物分类阶段,提取水饺二值图像中异物的圆度、长宽比、偏心率和灰度图像中异物最小外接矩形区域的灰度均值、方差、熵、三阶矩、7个灰度不变矩、LBP等76个特征构建特征向量,使用BP神经网络、支持向量机、K邻近、AdaBoost和朴素贝叶斯分类器对5种异物进行分类.实验结果表明,文中提出的识别方法对异物水饺图像的识别率达到99.52%;与Otsu分割算法、K-means分割算法、基于最大熵与遗传算法的分割算法(KSW-GA)、基于遗传神经网络的图像分割算法(GA-BP)相比,文中的分割算法分割结果更加精确; BP神经网络分类结果优于其他分类器,总体识别率达到98.90%.文中方法为食品中的异物在线自动检测提供了新的思路,对保证食品安全具有重要的现实意义.
In view of the fact that foreign bodies in boxed dumplings seriously endanger consumers' physical and mental health and that traditional metal detectors can only detect metals and the results cannot be visualized directly, X-ray imaging technology and image processing technology were used to automatically detect five kinds of foreign bodies in boxed dumplings, including steel balls, thin wires, screws, stones and glass. Firstly, we extracted LBP, HOG and Gabor texture features to construct feature vectors, and used Support Vector Machine to recognize foreign bodies in dumpling images. In the image segmentation stage, a threshold segmentation algorithm combining the maximum entropy algorithm of additional offset with the particle swarm optimization algorithm of linear decreasing weight was proposed. The algorithm added an offset function to the entropy of the image target area and took the total entropy of the image as the fitness function of particle swarm optimization algorithm to obtain the optimal threshold of image, and realized the image segmentation of foreign body dumplings. In the foreign body classification stage, the roundness, aspect ratio, eccentricity of the foreign objects in the binary image of the dumplings, and the gray mean, variance, entropy, third moment, the seven invariant moments, the LBP features of the minimum circumscribed rectangular area of the foreign bodies in the gray image were extracted to construct feature vectors. Then we used the BP neural network, Support Vector Machine, K-neighboring, AdaBoost and Naive-bayes classifier to classify five kinds of foreign bodies. The experimental results show that the recognition rate of the image recognition method for foreign body dumplings is 99.52%. Compared with segmentation algorithms of Otsu, K-means, the maximum entropy based genetic algorithm(KSW-GA), and genetic neural network(GA-BP) based, the segmentation result of proposed algorithm is more accurate. The classification results of BP neural network are superior to those classifiers, and the overall recognition rate is 98.90%. This study provides a new idea for on-line automatic detection of foreign bodies in food, and has important practical significance for ensuring food safety.
In view of the fact that foreign bodies in boxed dumplings seriously endanger consumers' physical and mental health and that traditional metal detectors can only detect metals and the results cannot be visualized directly, X-ray imaging technology and image processing technology were used to automatically detect five kinds of foreign bodies in boxed dumplings, including steel balls, thin wires, screws, stones and glass. Firstly, we extracted LBP, HOG and Gabor texture features to construct feature vectors, and used Support Vector Machine to recognize foreign bodies in dumpling images. In the image segmentation stage, a threshold segmentation algorithm combining the maximum entropy algorithm of additional offset with the particle swarm optimization algorithm of linear decreasing weight was proposed. The algorithm added an offset function to the entropy of the image target area and took the total entropy of the image as the fitness function of particle swarm optimization algorithm to obtain the optimal threshold of image, and realized the image segmentation of foreign body dumplings. In the foreign body classification stage, the roundness, aspect ratio, eccentricity of the foreign objects in the binary image of the dumplings, and the gray mean, variance, entropy, third moment, the seven invariant moments, the LBP features of the minimum circumscribed rectangular area of the foreign bodies in the gray image were extracted to construct feature vectors. Then we used the BP neural network, Support Vector Machine, K-neighboring, AdaBoost and Naive-bayes classifier to classify five kinds of foreign bodies. The experimental results show that the recognition rate of the image recognition method for foreign body dumplings is 99.52%. Compared with segmentation algorithms of Otsu, K-means, the maximum entropy based genetic algorithm(KSW-GA), and genetic neural network(GA-BP) based, the segmentation result of proposed algorithm is more accurate. The classification results of BP neural network are superior to those classifiers, and the overall recognition rate is 98.90%. This study provides a new idea for on-line automatic detection of foreign bodies in food, and has important practical significance for ensuring food safety.
引文
[1]Wang Xiaowei.The main characteristics and prospect of China’s frozen food industry development[J].Xiangcun Keji,2015(12):23-24(in Chinese)(王晓伟.我国速冻食品产业发展主要特点及前景分析[J].乡村科技,2015(12):23-24)
[2]Jin Xinxin,Pan Ligang,Wang Dong.Review on the source and detection technology of foreign bodies in food[J].Journal of Food Safety and Quality,2016,7(7):2803-2808(in Chinese)(靳欣欣,潘立刚,王冬.食品中异物种类来源及检测技术评述[J].食品安全质量检测学报,2016,7(7):2803-2808)
[3]Zhang Min,Cheng Xinfeng.Reflection on the deep processing and security of the frozen food in china[J].Journal of Jiangnan University:Humanities&Social Sciences,2014,13(1):114-117(in Chinese)(张慜,程新峰.对我国速冻食品行业加工深度及安全性的思考[J].江南大学学报:人文社会科学版,2014,13(1):114-117)
[4]Shi Xiaoya,Gao Lixia,Li Xin,et al.Applications of nondestructive detection technology in food safety rapid screening[J].Journal of Food Safety and Quality,2017,8(3):747-753(in Chinese)(史晓亚,高丽霞,李鑫,等.无损检测技术在食品安全快速筛查中的应用[J].食品安全质量检测学报,2017,8(3):747-753)
[5]Zou L,Ming S,Zhang D.A new method for rapid detection of the volume and quality of watermelon based on processing of X-ray images[C]//Proceedings of the International Conference on Computer and Computing Technologies in Agriculture.Heidelberg:Springer,2014,452:731-738
[6]Nielsen M S,Damkj?r K B,Feidenhans R.Quantitative in-situ monitoring of germinating barley seeds using X-ray dark-field radiography[J].Journal of Food Engineering,2017,198:98-104
[7]van Dael M,Lebotsa S,Herremans E,et al.A segmentation and classification algorithm for online detection of internal disorders in citrus using X-ray radiographs[J].Postharvest Biology and Technology,2016,112:205-214
[8]Diels E,van Dael M,Keresztes J,et al.Assessment of bruise volumes in apples using X-ray computed tomography[J].Postharvest Biology and Technology,2017,128:24-32
[9]Tao Y,Ibarra J G.Thickness-compensated X-ray imaging detec-tion of bone fragments in deboned poultry-model analysis[J].Transactions of the ASAE,2000,43(2):453-459
[10]Tao Y,Chen Z,Jing H,et al.Internal inspection of deboned poultry using X-ray imaging and adaptive thresholding[J].Transactions of the ASAE,2001,44(4):1005-1009
[11]Chen Z K,Tao Y,Chen X.Multiresolution local contrast enhancement of X-ray images for poultry meat inspection[J].Applied Optics,2001,40(8):1195-1200
[12]Mcfarlane N J B,Speller R D,Bull C R,et al.Detection of bone fragments in chicken meat using X-ray backscatter[J].Biosystems Engineering,2003,85(2):185-199
[13]Mery D,Lillo I,Loebel H,et al.Automated detection of fish bones in salmon fillets using X-ray testing[C]//Proceedings of the IEEE Image and Video Technology.Los Alamitos:IEEEComputer Society Press,2010:46-51
[14]Mery D,Lillo I,Loebel H,et al.Automated fish bone detection using X-ray imaging[J].Journal of Food Engineering,2011,105(3):485-492
[15]Nielsen M S,Lauridsen T,Christensen L B,et al.X-ray dark-field imaging for detection of foreign bodies in food[J].Food Control,2013,30(2):531-535
[16]Einarsdóttir H,Emerson M,Clemmensen L,et al.Novelty detection of foreign objects in food using multi-modal X-ray imaging[J].Food Control,2016,67:39-47
[17]Gonzalez R C,Woods R E,Eddins S L.Digital image processing using MATLAB[M].2nd ed.Beijing:Tsinghua University Press,2013(in Chinese)(Gonzalez R C,Woods R E,Eddins S L.数字图像处理的MATLAB实现[M].阮秋琦,译.2版.北京:清华大学出版社,2013)
[18]Zhang Chengliang,Li Lei,Dong Quancheng,et al.Recognition for machine picking seed cotton impurities based on GA-SVMmodel[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(24):189-196(in Chinese)(张成梁,李蕾,董全成,等.基于GA-SVM模型的机采籽棉杂质识别[J].农业工程学报,2016,32(24):189-196)
[19]Zhang Zheng,Xu Chao,Ren Shuxia,et al.Digital image and machine vision:Visual C++and Matlab[M].Beijing:Posts and Telecom Press,2014(in Chinese)(张铮,徐超,任淑霞,等.数字图像与机器视觉:Visual C++与Matlab实现[M].北京:人民邮电出版社,2014)
[20]Chen Jun,Huang Lifeng,Gao Chengying,et al.Gender recognition based on weighted combination of Gabor wavelets[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(9):1767-1774(in Chinese)(陈君,黄立峰,高成英,等.基于Gabor小波加权组合特征的性别识别[J].计算机辅助设计与图形学学报,2015,27(9):1767-1774)
[21]Wan Yuan,Li Huanhuan,Wu Kefeng,et al.Fusion with Layered features of LBP and HOG for face recognition[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(4):640-650(in Chinese)(万源,李欢欢,吴克风,等.LBP和HOG的分层特征融合的人脸识别[J].计算机辅助设计与图形学学报,2015,27(4):640-650)
[22]Wen Zheng,Sun Huake.Matlab intelligent algorithm[M].Beijing:Tsinghua University Press,2017(in Chinese)(温正,孙华克.MATLAB智能算法[M].北京:清华大学出版社,2017)
[23]Yang Xinting,Sun Wenjuan,Li Ming,et al.Water droplets fluo-rescence image segmentation of cucumber leaves based on K-means clustering with opening and closing alternately filter-ing[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(17):136-143(in Chinese)(杨信廷,孙文娟,李明,等.基于K均值聚类和开闭交替滤波的黄瓜叶片水滴荧光图像分割[J].农业工程学报,2016,32(17):136-143)
[24]LüYahui,Yun Wenju,Zhang Chao,et al.Multi-characteristic comprehensive recognition of weil-facilitied farmland based on TOPSIS and BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(3):196-204(in Chinese)(吕雅慧,郧文聚,张超,等.基于TOPSIS和BP神经网络的高标准农田综合识别[J].农业机械学报,2018,49(3):196-204)
[25]Liu Shijing,Wang Shuai,Chen Jun,et al.Moving larval shrimps recognition based on improved principal component analysis and AdaBoost[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(1):212-218(in Chinese)(刘世晶,王帅,陈军,等.基于改进主成分分析和AdaBoost算法的运动虾苗识别方法[J].农业工程学报,2017,33(1):212-218)
[26]Zhai Zhifen,Xu Zhe,Zhou Xinqun,et al.Recognition of hazard grade for cotton blind stinkbug based on Naive Bayesian classifier[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(1):204-211(in Chinese)(翟治芬,徐哲,周新群,等.基于朴素贝叶斯分类器的棉花盲椿象危害等级识别[J].农业工程学报,2015,31(1):204-211)
[2]Jin Xinxin,Pan Ligang,Wang Dong.Review on the source and detection technology of foreign bodies in food[J].Journal of Food Safety and Quality,2016,7(7):2803-2808(in Chinese)(靳欣欣,潘立刚,王冬.食品中异物种类来源及检测技术评述[J].食品安全质量检测学报,2016,7(7):2803-2808)
[3]Zhang Min,Cheng Xinfeng.Reflection on the deep processing and security of the frozen food in china[J].Journal of Jiangnan University:Humanities&Social Sciences,2014,13(1):114-117(in Chinese)(张慜,程新峰.对我国速冻食品行业加工深度及安全性的思考[J].江南大学学报:人文社会科学版,2014,13(1):114-117)
[4]Shi Xiaoya,Gao Lixia,Li Xin,et al.Applications of nondestructive detection technology in food safety rapid screening[J].Journal of Food Safety and Quality,2017,8(3):747-753(in Chinese)(史晓亚,高丽霞,李鑫,等.无损检测技术在食品安全快速筛查中的应用[J].食品安全质量检测学报,2017,8(3):747-753)
[5]Zou L,Ming S,Zhang D.A new method for rapid detection of the volume and quality of watermelon based on processing of X-ray images[C]//Proceedings of the International Conference on Computer and Computing Technologies in Agriculture.Heidelberg:Springer,2014,452:731-738
[6]Nielsen M S,Damkj?r K B,Feidenhans R.Quantitative in-situ monitoring of germinating barley seeds using X-ray dark-field radiography[J].Journal of Food Engineering,2017,198:98-104
[7]van Dael M,Lebotsa S,Herremans E,et al.A segmentation and classification algorithm for online detection of internal disorders in citrus using X-ray radiographs[J].Postharvest Biology and Technology,2016,112:205-214
[8]Diels E,van Dael M,Keresztes J,et al.Assessment of bruise volumes in apples using X-ray computed tomography[J].Postharvest Biology and Technology,2017,128:24-32
[9]Tao Y,Ibarra J G.Thickness-compensated X-ray imaging detec-tion of bone fragments in deboned poultry-model analysis[J].Transactions of the ASAE,2000,43(2):453-459
[10]Tao Y,Chen Z,Jing H,et al.Internal inspection of deboned poultry using X-ray imaging and adaptive thresholding[J].Transactions of the ASAE,2001,44(4):1005-1009
[11]Chen Z K,Tao Y,Chen X.Multiresolution local contrast enhancement of X-ray images for poultry meat inspection[J].Applied Optics,2001,40(8):1195-1200
[12]Mcfarlane N J B,Speller R D,Bull C R,et al.Detection of bone fragments in chicken meat using X-ray backscatter[J].Biosystems Engineering,2003,85(2):185-199
[13]Mery D,Lillo I,Loebel H,et al.Automated detection of fish bones in salmon fillets using X-ray testing[C]//Proceedings of the IEEE Image and Video Technology.Los Alamitos:IEEEComputer Society Press,2010:46-51
[14]Mery D,Lillo I,Loebel H,et al.Automated fish bone detection using X-ray imaging[J].Journal of Food Engineering,2011,105(3):485-492
[15]Nielsen M S,Lauridsen T,Christensen L B,et al.X-ray dark-field imaging for detection of foreign bodies in food[J].Food Control,2013,30(2):531-535
[16]Einarsdóttir H,Emerson M,Clemmensen L,et al.Novelty detection of foreign objects in food using multi-modal X-ray imaging[J].Food Control,2016,67:39-47
[17]Gonzalez R C,Woods R E,Eddins S L.Digital image processing using MATLAB[M].2nd ed.Beijing:Tsinghua University Press,2013(in Chinese)(Gonzalez R C,Woods R E,Eddins S L.数字图像处理的MATLAB实现[M].阮秋琦,译.2版.北京:清华大学出版社,2013)
[18]Zhang Chengliang,Li Lei,Dong Quancheng,et al.Recognition for machine picking seed cotton impurities based on GA-SVMmodel[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(24):189-196(in Chinese)(张成梁,李蕾,董全成,等.基于GA-SVM模型的机采籽棉杂质识别[J].农业工程学报,2016,32(24):189-196)
[19]Zhang Zheng,Xu Chao,Ren Shuxia,et al.Digital image and machine vision:Visual C++and Matlab[M].Beijing:Posts and Telecom Press,2014(in Chinese)(张铮,徐超,任淑霞,等.数字图像与机器视觉:Visual C++与Matlab实现[M].北京:人民邮电出版社,2014)
[20]Chen Jun,Huang Lifeng,Gao Chengying,et al.Gender recognition based on weighted combination of Gabor wavelets[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(9):1767-1774(in Chinese)(陈君,黄立峰,高成英,等.基于Gabor小波加权组合特征的性别识别[J].计算机辅助设计与图形学学报,2015,27(9):1767-1774)
[21]Wan Yuan,Li Huanhuan,Wu Kefeng,et al.Fusion with Layered features of LBP and HOG for face recognition[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(4):640-650(in Chinese)(万源,李欢欢,吴克风,等.LBP和HOG的分层特征融合的人脸识别[J].计算机辅助设计与图形学学报,2015,27(4):640-650)
[22]Wen Zheng,Sun Huake.Matlab intelligent algorithm[M].Beijing:Tsinghua University Press,2017(in Chinese)(温正,孙华克.MATLAB智能算法[M].北京:清华大学出版社,2017)
[23]Yang Xinting,Sun Wenjuan,Li Ming,et al.Water droplets fluo-rescence image segmentation of cucumber leaves based on K-means clustering with opening and closing alternately filter-ing[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(17):136-143(in Chinese)(杨信廷,孙文娟,李明,等.基于K均值聚类和开闭交替滤波的黄瓜叶片水滴荧光图像分割[J].农业工程学报,2016,32(17):136-143)
[24]LüYahui,Yun Wenju,Zhang Chao,et al.Multi-characteristic comprehensive recognition of weil-facilitied farmland based on TOPSIS and BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(3):196-204(in Chinese)(吕雅慧,郧文聚,张超,等.基于TOPSIS和BP神经网络的高标准农田综合识别[J].农业机械学报,2018,49(3):196-204)
[25]Liu Shijing,Wang Shuai,Chen Jun,et al.Moving larval shrimps recognition based on improved principal component analysis and AdaBoost[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(1):212-218(in Chinese)(刘世晶,王帅,陈军,等.基于改进主成分分析和AdaBoost算法的运动虾苗识别方法[J].农业工程学报,2017,33(1):212-218)
[26]Zhai Zhifen,Xu Zhe,Zhou Xinqun,et al.Recognition of hazard grade for cotton blind stinkbug based on Naive Bayesian classifier[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(1):204-211(in Chinese)(翟治芬,徐哲,周新群,等.基于朴素贝叶斯分类器的棉花盲椿象危害等级识别[J].农业工程学报,2015,31(1):204-211)