Abstract
Objective: Solve the problems of low detection efficiency and poor accuracy in existing food freshness recognition methods. Methods: Based on the food production line image acquisition system, an improved residual neural network model was proposed for food freshness recognition on the production line. The improved LRELU activation function was introduced to improve the recognition performance of the model, the batch normalization layer was introduced to improve the training efficiency of the model, and the Dropout layer was introduced to discard a certain proportion of neurons to reduce the impact of over fitting. Results: Compared with conventional food freshness recognition methods, the experimental method could accurately and efficiently achieve food freshness recognition, with an overall freshness recognition accuracy of >97%, average recognition time of 9.8 ms, which meet the needs of food production lines for freshness recognition. Conclusion: The detection method based on deep learning is a non-destructive, efficient, and high-precision method for recognizing the freshness of food images.
Publication Date
10-30-2023
First Page
123
Last Page
127
DOI
10.13652/j.spjx.1003.5788.2023.60073
Recommended Citation
Wei, WAN; Yingxue, PU; Xiang, WANG; and Chao, LI
(2023)
"Food freshness recognition method based on improved ResNet model,"
Food and Machinery: Vol. 39:
Iss.
9, Article 19.
DOI: 10.13652/j.spjx.1003.5788.2023.60073
Available at:
https://www.ifoodmm.cn/journal/vol39/iss9/19
References
[1] 杨森, 冯全, 张建华, 等. 基于轻量卷积网络的马铃薯外部缺陷无损分级[J]. 食品科学, 2021, 42（10）: 284-289.
YANG S, FENG Q, ZHANG J H, et al. Non destructive grading of potato external defects based on lightweight convolution network[J]. Food Science, 2021, 42（10）: 284-289.
[2] 张思雨, 张秋菊, 李可. 采用机器视觉与自适应卷积神经网络检测花生仁品质[J]. 农业工程学报, 2020, 36（4）: 269-277.
ZHANG S Y, ZHANG Q J, LI K. Using machine vision and adaptive convolution neural network to detect peanut kernel quality[J]. Journal of Agricultural Engineering, 2020, 36（4）: 269-277.
[3] 海潮, 赵凤霞, 孙烁. 基于Blob分析的红枣表面缺陷在线检测技术[J]. 食品与机械, 2018, 34（1）: 126-129.
HAI C, ZHAO F X, SUN S. On line detection technology of jujube surface defects based on Blob analysis[J]. Food & Machinery, 2018, 34（1）: 126-129.
[4] 张涛, 刘玉婷, 杨亚宁, 等. 基于机器视觉的表面缺陷检测研究综述[J]. 科学技术与工程, 2020, 20（35）: 14 366-14 376.
ZHANG T, LIU Y T, YANG Y N, et al. Review of research on surface defect detection based on machine vision[J]. Science Technology and Engineering, 2020, 20（35）: 14 366-14 376.
[5] 肖旺, 杨煜俊, 申启访, 等. 基于改进的GoogLeNet鸭蛋表面缺陷检测[J]. 食品与机械, 2021, 37（6）: 162-167.
XIAO W, YANG Y J, SHEN Q F, et al. Detection of duck egg surface defects based on improved GoogLeNet[J]. Food & Machinery, 2021, 37（6）: 162-167.
[6] 杨志锐, 郑宏, 郭中原, 等. 基于网中网卷积神经网络的红枣缺陷检测[J]. 食品与机械, 2020, 36（2）: 140-145, 181.
YANG Z R, ZHENG H, GUO Z Y, et al. Chinese date defect detection based on net in net convolution neural network[J]. Food & Machinery, 2020, 36 （2）: 140-145, 181.
[7] 沈海军, 张汤磊, 许振兴, 等. 基于Fisher判别分析对苹果新鲜度的识别研究[J]. 食品工业科技, 2023, 44（4）: 361-368.
SHEN H J, ZHANG T L, XU Z X, et al. Recognitionof apple freshness based on fisher discriminant analysis[J]. Science and Technology of Food Industry, 2023, 44（4）: 361-368.
[8] 刘雪, 沈长盈, 吕学泽, 等. 基于改进 MobileNetV3-Large的鸡蛋新鲜度识别模型[J]. 农业工程学报, 2022, 38（17）: 196-204.
LIU X, SHEN C Y, LU X Z, et al. An improved MobileNetV3-Large based egg freshness recognition model[J]. Journal of Agricultural Engineering, 2022, 38（17）: 196-204.
[9] 焦俊, 王文周, 侯金波, 等. 基于改进残差网络的黑毛猪肉新鲜度识别方法[J]. 农业机械学报, 2019, 50（8）: 364-371.
JIAO J, WANG W Z, HOU J B, et al. A method for identifying the freshness of black haired pork based on improved residualnetwork[J]. Journal of Agricultural Machinery, 2019, 50（8）: 364-371.
[10] 董鑫鑫, 杨方威, 于航, 等. 基于拉曼光谱技术的猪瘦肉新鲜度快速无损检测方法研究[J]. 光谱学与光谱分析, 2023, 43（2）: 484-488.
DONG X X, YANG F W, YU H, et al. Research on a rapid and non-destructive detection method for the freshness of pork lean meat based on Raman spectroscopy technology[J]. Spectroscopy and Spectral Analysis, 2023, 43（2）: 484-488.
[11] 王云鹏, 司海平, 宋佳珍, 等. 基于红外与可见光图像融合的苹果表面缺陷检测方法[J]. 食品与机械, 2021, 37（12）: 127-131.
WANG Y P, SI H P, SONG J Z, et al. Apple surface defect detection method based on infrared and visible image fusion[J]. Food & Machinery, 2021, 37（12）: 127-131.
[12] 薛勇, 王立扬, 张瑜, 等. 基于 GoogLeNet 深度迁移学习的苹果缺陷检测方法[J]. 农业机械学报, 2020, 51（7）: 30-35.
XUE Y, WANG L Y, ZHANG Y, et al. Apple defect detection method based onGoogLeNet deep migration learning[J]. Journal of Agricultural Machinery, 2020, 51（7）: 30-35.
[13] 周靖宇, 孙锐, 余多, 等. 基于近红外技术和偏最小二乘判别法对无花果成熟度的快速判别[J]. 食品与机械, 2020, 36（11）: 107-111.
ZHOU J Y, SUN R, YU D, et al. Rapid identification of fig maturity based on near infrared technology and partial least squares method[J]. Food & Machinery, 2020, 36（11）: 107-111.
[14] 张铮, 熊盛辉, 王孙强, 等. 基于机器视觉的香蕉果肉缺陷预测方法[J]. 食品与机械, 2020, 36（7）: 150-154.
ZHANG Z, XIONG S H, WANG S Q, et al. Prediction method of banana pulp defects based on machine vision[J]. Food & Machinery, 2020, 36（7）: 150-154.
[15] 杨晨昱, 袁鸿飞, 马惠玲, 等. 基于傅里叶近红外光谱和电子鼻技术的苹果霉心病无损检测[J]. 食品与发酵工业, 2021, 47（7）: 211-216.
YANG C Y, YUAN H F, MA H L, et al. Nondestructive detection of applemycoheart disease based on Fourier near infrared spectroscopy and electronic nose technology[J]. Food and Fermentation Industry, 2021, 47（7）: 211-216.
[16] 任二芳, 牛德宝, 温立香, 等. 电子鼻和电子舌在水果检测中的应用进展[J]. 食品工业, 2019, 40（10）: 261-264.
REN E F, NIU D B, WEN L X, et al. Application progress of electronic nose and electronic tongue in fruit detection[J]. Food Industry, 2019, 40（10）: 261-264.
[17] 刘芳, 刘玉坤, 林森, 等. 基于改进型YOLO的复杂环境下番茄果实快速识别方法[J]. 农业机械学报, 2020, 51（6）: 229-237.
LIU F, LIU Y K, LIN S, et al. Rapid identification method of tomato fruit in complex environment based on improved Yolo[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51（6）: 229-237.
[18] 宋海涛, 何文浩, 原魁. 一种基于SIFT特征的机器人环境感知双目立体视觉系统[J]. 控制与决策, 2019, 34（7）: 1 545-1 552.
SONG H T, HE W H, YUAN K. A robot environment perception binocular stereo vision system based on SIFT feature[J]. Control and Decision, 2019, 34（7）: 1 545-1 552.
[19] 冯喆, 李卫豪, 崔笛. 基于高光谱成像和深度学习的山核桃内源性异物检测[J]. 农业机械学报, 2021, 52（S1）: 466-471.
FENG Z, LI Z H, CUI D. Detection of endogenous foreign bodies in pecan based on hyperspectral imaging and deep learning[J]. Journal of Agricultural Machinery, 2021, 52（S1）: 466-471.
[20] 王红霞, 周家奇, 辜承昊, 等. 用于图像分类的卷积神经网络中激活函数的设计[J]. 浙江大学学报（工学版）, 2019, 53（7）: 1 363-1 373.
WANG H X, ZHOU J Q, GU C H, et al. Design of activation function in convolutional neural network for image classification[J]. Journal of Zhejiang University （Engineering Edition）, 2019, 53（7）: 1 363-1 373.
[21] 陈远涛, 熊忆舟, 薛莹莹, 等. 基于深度学习的电子鼻食品新鲜度检测与识别技术研究[J]. 传感技术学报, 2021, 34（8）: 1 131-1 138.
CHEN Y T, XIONG Y Z, XUE Y Y, et al. Research on electronic nose food freshness detection and recognition technology based on deep learning[J]. Journal of Sensing Technology, 2021, 34（8）: 1 131-1 138.