Abstract
Objective:This study focuses on solving the problems that stem and calyx are mistakenly recognized as defective jujube in the current detection process of jujube.Methods:A method for identifying stem / calyx and defects of dried Hami jujube based on deep learning and image processing was proposed. By improving the depth residual network ResNeXt-50, using the region of interest extraction method and transfer learning technology, TL-ROI-X-ResNeXt-50 classification model was proposed to realize the classification of stem / calyx and defects of dried Hami jujube.Results:Through the comparison of model experiments, the region of interest extraction method and transfer learning technology could reduce the calculation cost of the model and improve the accuracy. The accuracy of model recognition could reached 94.17%.Conclusion:The method can initially meet the production requirements of on-line detection equipment for stem / calyx and defects of dried Hami jujube, and provide theoretical basis and technical reference for the development of rapid nondestructive detection system for stem / calyx and defects of other similar fruits.
Publication Date
7-4-2022
First Page
133
Last Page
138
DOI
10.13652/j.issn.1003-5788.2022.01.021
Recommended Citation
Cong, LI; Guo-wei, YU; Yuan-jia, ZHANG; and Ben-xue, MA
(2022)
"Research on recognition of stem/calyx and defects of dried Hami jujube based on ResNeXt and transfer learning,"
Food and Machinery: Vol. 38:
Iss.
1, Article 21.
DOI: 10.13652/j.issn.1003-5788.2022.01.021
Available at:
https://www.ifoodmm.cn/journal/vol38/iss1/21
References
[1] 孙静涛,马本学,董娟,等.基于特征波长提取的哈密大枣可溶性固形物的高光谱预测[J].现代食品科技,2016,32(9):174-179.SUN Jing-tao,MA Ben-xue,DONG Juan,et al.Characteristic wavelength selection-based prediction of soluble solids content of hami big jujubes using the hyperspectral imaging technology[J].Modern Food Science and Technology,2016,32(9):174-179.
[2] 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 Chao,ZHAO Feng-xia,SUN Shuo,et al.Research on online detection jujube surface defectsbased on blob analysis[J].Food & Machinery,2018,34(1):126-129.
[3] 张萌,许敏.红枣表面缺陷快速检测方法研究[J].江苏农业科学,2015,43(7):331-334.ZHANG Meng,XU Min.Study on rapid detection method of surface defects of jujube[J].Jiangsu Agricultural Sciences,2015,43(7):331-334.
[4] 曾窕俊,吴俊杭,马本学,等.基于帧间路径搜索和E-CNN的红枣定位与缺陷检测[J].农业机械学报,2019,50(2):307-314.ZENG Tiao-jun,WU Jun-hang,MA Ben-xue,et al.Localization and defect detection of jujubes based on search of shortest path between frames and ensemble-CNN model[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(2):307-314.
[5] WU Long-guo,HE Jian-guo,LIU Gui-san,et al.Detection of common defects on jujube using Vis-NIR and NIR hyperspectral imaging[J].Postharvest Biologyand Technology,2016,112:134-142.〖HJ1.75mm〗
[6] 卢伟,胡海阳,王家鹏,等.基于卷积神经网络面部图像识别的拖拉机驾驶员疲劳检测[J].农业工程学报,2018,34(7):192-199.LU Wei,HU Hai-yang,WANG Jia-peng,et al.Tractor driver fatigue detection based on convolution neural network and facial image recognition[J].Transactions of the Chinese Society of Agricultural Engineering,2018,34(7):192-199.
[7] 缪裕青,邹巍,刘同来,等.基于参数迁移和卷积循环神经网络的语音情感识别[J].计算机工程与应用,2019,55(10):135-140.MIAO Yu-qing,ZOU Wei,LIU Tong-lai,et al.Speech emotion recognition model based on parameter transfer and convolutional recurrent neural network[J].Computer Engineering and Applications,2019,55(10):135-140.
[8] CHO S W,BAEK N R,KIM M C,et al.Face detection in nighttime images using Visible-light camera sensors with Two-step faster Region-based convolutional neural network[J].Sensors,2018,18(9):2 995.
[9] 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.YANG Zhi-rui,ZHENG Hong,GUO Zhong-yuan,et al.Detection of jujubes based on the neural network with network convolution[J].Food & Machinery,2020,36(2):140-145.
[10] 方双,赵凤霞,楚松峰,等.基于多尺度卷积神经网络的缺陷红枣检测方法[J].食品与机械,2021,37(2):158-163.FANG Shuang,ZHAO Feng-xia,CHU Feng-song,et al.Defective jujube detection technology based on multi-scale convolution neural network[J].Food & Machinery,2021,37(2):158-163.
[11] XU Xiao-han,ZHENG Hong,YOU Chang-hui,et al.FAR-Net:Feature-wise Attention-based relation network for multilabel jujube defect classification[J].Sensors,2021,21(2):1-17.
[12] JU Jian-ping,HONG Zheng,XU Xiao-chang.Classification of jujube defects in small data sets based on transfer learning[J].Neural Computing and Applications,2021.DOI:10.1007/s00521-021-05715-2.
[13] LIU Shao-ping,TIAN Guo-hui,YUAN Xu,et al.A novel scene classification model combining ResNet based transfer learning and data augmentation with a filter[J].Neurocomputing,2019,338:191-206.
[14] HE Kai-ming,ZHANG Xiao-yu,REN Shao-qing,et al.Deep residual learning for image recognition[J].IEEE Conference on Computer Vision and Pattern Recognition,2016.DOI:10.1109/CVPR.2016.90.
[15] 李轩屹,朱晓军.多尺度深度CNN的糖尿病视网膜病变分类[J].计算机工程与设计,2020,41(11):3 229-3 234.LI Xuan-yi,ZHU Xiao-jun.Classification of diabetic retinopathy with multi-scale depth CNN[J].Computer Engineering and Design,2020,41(11):3 229-3 234.
[16] 赵立新,侯发东,吕正超,等.基于迁移学习的棉花叶部病虫害图像识别[J].农业工程学报,2020,36(7):184-191.ZHAO Li-xin,HOU Fa-dong,LU Zheng-chao,et al.Image recognition of cotton leaf diseases andpests based on transfer learning[J].Transactions of the Chinese Society of Agricultural Engineering,2020,36(7):184-191.
[17] 黄双萍,孙超,齐龙,等.基于深度卷积神经网络的水稻穗瘟病检测方法[J].农业工程学报,2017,33(20):169-176.HUANG Shuang-ping,SUN Chao,QI Long,et al.Rice panicle blast identification method based on deep convolution neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(20):169-176.