Abstract
In this paper, a method based on a multi-scale convolutional neural network for detecting defects in jujube is proposed. Parallel multi-scale convolution modules were added to the AlexNet convolutional neural network to increase the depth and width of the network and reduce the parameters in the network; Added batch normalization processing to the convolutional layer to reduce changes in data distribution during training and improve the generalization ability of the network. Taking the yellow-skinned jujube, moldy jujube, broken-head jujube and normal jujube in Xinjiang dried jujube as the research objects, these dried jujubes were trained and verified. The results showed that the recognition rates of this model for yellow-skinned jujubes, moldy jujubes, broken-head jujubes and normal jujubes were 96.67%, 96.25%, 98.57%, and 97.14% respectively, and the comprehensive recognition rate could reach 97.14%. Compared with other algorithms, this algorithm was more robust and had higher accuracy in identifying defective red jujubes.
Publication Date
2-28-2021
First Page
158
Last Page
163,168
DOI
10.13652/j.issn.1003-5788.2021.02.027
Recommended Citation
Shuang, FANG; Feng-xia, ZHAO; Song-feng, CHU; and Zhen-hua, WU
(2021)
"Defective jujube detection technology based on multi-scale convolutional neural network,"
Food and Machinery: Vol. 37:
Iss.
2, Article 27.
DOI: 10.13652/j.issn.1003-5788.2021.02.027
Available at:
https://www.ifoodmm.cn/journal/vol37/iss2/27
References
[1] 中国国家标准化管理委员会. 干制红枣: GB/T 5835—2009[S]. 北京: 中国标准出版社, 2009: 2.
[2] 钟小华, 曹玉华, 张永清, 等. 基于机器视觉技术的红枣全表面信息无损分拣系统研究与实现[J]. 食品与机械, 2017, 33(5): 114-118.
[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.
[4] 詹映, 罗华平, 彭云发, 等. BP人工神经网络南疆红枣颜色分级方法的研究[J]. 食品工业, 2015, 36(1): 165-167.
[5] 苏军, 饶元, 张敬尧, 等. 基于GA优化SVM的干制红枣品种分类方法[J]. 洛阳理工学院学报(自然科学版), 2018, 28(4): 68-72, 96.
[6] KAMILARIS A, PRENAFETA-BOLDU F. Deep learning in agriculture: A survey[J]. Computers and Electronics in Agriculture, 2018, 147: 70-90.
[7] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[8] LI Ya, WANG Guang-run, NIE Lin, et al. Distance metric optimization driven convolutional neural network for age invariant face recognition[J]. Pattern Recognition, 2018, 75: 51-62.
[9] SINGH R, OM H. Newborn face recognition using deep convolutional neural network[J]. Multimedia Tools & Applications, 2017, 76(18): 1-11.
[10] YANG Wei-xin, JIN Lian-wen, TAO De-cheng, et al. DropSample: A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten chinese character recognition[J]. Pattern Recognition, 2016, 58: 190-203.
[11] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016, 42(9): 1 300-1 312.
[12] 曾窕俊, 吴俊航, 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.
[13] 文怀兴, 王俊杰, 韩昉. 基于改进残差网络的红枣缺陷检测分类方法研究[J]. 食品与机械, 2020, 36(1): 161-165.
[14] 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.
[15] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[16] LOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]// International Conference on MachineLearning(ICML). New York: [s.n.], 2015: 448-456.
[17] 程鸿芳, 张春友. 自然场景下基于改进LeNet卷积神经网络的苹果图像识别技术[J]. 食品与机械, 2019, 35(3): 155-158.
[18] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2015(7): 1 409-1 556.
[19] BAKHODAA, YUAN G L, FUNG W W L, et al. Analyzing CUDA workloads using a detailed GPU simulator[C]// 2009 IEEE International Symposium on Performance Analysis of Systems and Software. [S.l.]: IEEE, 2009: 163-174.
[20] SZEGEDY C, LIU W, JIA Y, et al. Goingdeeper with convolutions[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015: 1-9.