Abstract
Objective: To solve the problems of low accuracy and poor efficiency in existing apple defect detection methods. Methods: Based on a fruit image acquisition system, an improved convolutional neural network was proposed for detecting surface defects in apples. Deep separable convolution was Introduced to replace the original network standard convolution, to improve the speed of feature extraction. The Leaky ReLU activation function was introduced to replace the ReLU activation function to improve the calculation efficiency and accuracy. Global average pooling was introduced to replace the fully connected layer, to reduce the computational complexity of the network model. After each layer of convolution, a batch normalization layer was added, and its superiority was verified through comparative analysis between experiments and conventional methods. Results: Compared with conventional methods, the proposed method had higher detection accuracy and speed in apple defect detection, and had fewer model parameters, with an accuracy rate of 99.60%, a detection speed of 526 FPS, and a model parameter quantity of 389 072. Conclusion: This apple defect detection method can effectively reduce model parameters and detection time, with high accuracy and speed.
Publication Date
10-20-2023
First Page
155
Last Page
160
DOI
10.13652/j.spjx.1003.5788.2023.60019
Recommended Citation
Guo-zhen, DU; Ming-xing, LU; Ze-xu, JI; and Ji-chao, LIU
(2023)
"Research on apple defect detection method based on improved CNN,"
Food and Machinery: Vol. 39:
Iss.
6, Article 24.
DOI: 10.13652/j.spjx.1003.5788.2023.60019
Available at:
https://www.ifoodmm.cn/journal/vol39/iss6/24
References
[1] 姜洪权, 贺帅, 高建民, 等. 一种改进卷积神经网络模型的焊缝缺陷识别方法[J]. 机械工程学报, 2020, 56（8）: 235-242.
JIANG C Q, HE S, GAO J M, et al. An improved method of welding seam defect recognition based on convolutional neural network model[J]. Chinese Journal of Mechanical Engineering, 2020, 56（8）: 235-242.
[2] 项辉宇, 薛真, 冷崇杰, 等. 基于Halcon的苹果品质视觉检测试验研究[J]. 食品与机械, 2016, 32（10）: 123-126.
XIANG H Y, XUE Z, LENG C J, et al. Experimental study on visual inspection of apple quality based on Halcon[J]. Food & Machinery, 2016, 32 （10）: 123-126.
[3] 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 classification of potato external defects based on lightweight convolutional network[J]. Food Science, 2021, 42（10）: 284-289.
[4] 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 convolutional neural network to detect the quality of peanut kernels[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36（4）: 269-277.
[5] 程磊. 基于改进粒子群算法的苹果表面缺陷检测[J]. 食品与机械, 2018, 34（3）: 141-145.
CHENG L. Apple surface defect detection based on improved particle swarm optimization algorithm[J]. Food & Machinery, 2018, 34（3）: 141-145.
[6] 刘云, 杨建滨, 王传旭. 基于卷积神经网络的苹果缺陷检测算法[J]. 电子测量技术, 2017, 40（3）: 108-112.
LIU Y, YANG J B, WANG C X. Apple defect detection algorithm based on convolutional neural network[J]. Electronic Measurement Technology, 2017, 40（3）: 108-112.
[7] 周雨帆, 李胜旺, 杨奎河, 等. 基于轻量级卷积神经网络的苹果表面缺陷检测方法[J]. 河北工业科技, 2021, 38（5）: 388-394.
ZHOU Y F, LI S W, YANG K H, et al. Apple surface defect detection method based on lightweight convolutional neural network[J]. Hebei Industrial Technology, 2021, 38（5）: 388-394.
[8] 梅金波, 李涛, 秦寅初. 苹果采摘机器人监测系统和表面缺陷检测方法研究[J/OL]. 计算机测量与控制. （2023-01-19） [2023-02-04]. https://kns.cnki.net/kcms/detail//11.4762.tp.20230118.1122.006.html.
MEI J B, LI T, QIN Y C. Research on apple picking robot monitoring system and surface defect detection methods[J/OL]. Computer Measurement and Control. （2023-01-19） [2023-02-04]. https://kns.cnki.net/kcms/detail//11.4762.tp.20230118.1122.006.html.
[9] GEETHARAMANI G, ARUN PANDIAN J. Identification of plant leaf diseases using a nine-layer deep convolutional neural network[J]. Computers and Electrical Engineering, 2019, 76: 323-338.
[10] LIU B, ZHANG Y, HE D J, et al. Identification ofapple leaf diseases based on deep convolutional neural networks[J]. Symmetry, 2017, 10（1）: 11.
[11] 董腾, 秦腾飞, 张如如, 等. 基于机器视觉的水果分拣系统[J]. 聊城大学学报（自然科学版）, 2017, 30（1）: 93-96.
DONG T, QIN T F, ZHANG R R, et al. Fruit sorting system based on machine vision[J]. Journal of Liaocheng University （Natural Science Edition）, 2017, 30（1）: 93-96.
[12] 周伟, 徐颖若. 基于PLC和图像处理的水果分类智能控制系统[J]. 农机化研究, 2021, 12（5）: 235-239.
ZHOU W, XU Y R. Intelligent control system of fruit classification based on PLC and image processing[J]. Agricultural Mechanization Research, 2021, 12（5）: 235-239.
[13] 赵小霞, 李志强. 基于PLC和机器视觉的水果自动分级系统研究[J]. 农机化研究, 2021, 12（8）: 75-79.
ZHAO X X, LI Z Q. Research on automatic fruit grading system based on PLC and machine vision[J]. Agricultural Mechanization Research, 2021, 12（8）: 75-79.
[14] 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 red jujube surface defects based on Blobanalysis[J]. Food & Machinery, 2018, 34（1）: 126-129.
[15] 杨双艳, 杨紫刚, 张四伟, 等. 基于近红外光谱和PSO-SVM算法的烟叶自动分级方法[J]. 贵州农业科学, 2018, 46（12）: 141-144.
YANG S Y, YANG Z G, ZHAGN S W, et al. Automatic tobacco grading method based on near infraredspectroscopy and PSO-SVM algorithm[J]. Guizhou Agricultural Sciences, 2018, 46（12）: 141-144.
[16] 王阳阳, 黄勋, 陈浩, 等. 基于同态滤波和改进K-means的苹果分级算法研究[J]. 食品与机械, 2019, 35（12）: 47-51, 112.
WANG Y Y, HUANG X, CHEN H, et al. Apple grading algorithm based on homomorphic filtering and improved K-means[J]. Food & machinery, 2019, 35（12）: 47-51, 112.
[17] 王立扬, 张瑜, 沈群, 等. 基于改进型LeNet-5的苹果自动分级方法[J]. 中国农机化学报, 2020, 41（7）: 105-110.
WANG L Y, ZHANG Y, SHEN Q, et al. Automatic apple classification method based on improvedlenet-5[J]. Chinese Journal of Agricultural Mechanochemistry, 2020, 41（7）: 105-110.
[18] 于蒙, 李雄, 杨海潮, 等. 基于图像识别的苹果的等级分级研究[J]. 自动化与仪表, 2019, 34（7）: 39-43.
YU M, LI X, YANG H C, et al. Apple grading based on image recognition[J]. Automation and Instrumentation, 2019, 34（7）: 39-43.
[19] 樊泽泽, 柳倩, 柴洁玮, 等. 基于颜色与果径特征的苹果树果实检测与分级[J]. 计算机工程与科学, 2020, 42（9）: 1 599-1 607.
FAN Z Z, LIU Q, CHAI J W, et al. Apple fruit detection and grading based on color and fruit diameter characteristics[J]. Computer Engineering and Science, 2020, 42（9）: 1 599-1 607.
[20] 王冉冉, 刘鑫, 尹孟, 等. 面向苹果硬度检测仪的声振信号激励与采集系统设计[J]. 浙江大学学报（农业与生命科学版）, 2020, 46（1）: 111-118.
WANG R R, LIU X, YIN M, et al. Design of acoustic vibration signal excitation and acquisition system for apple hardness tester[J]. Journal of Zhejiang University （Agriculture and Life Sciences Edition）, 2020, 46（1）: 111-118.
[21] 刘英, 周晓林, 胡忠康, 等. 基于优化卷积神经网络的木材缺陷检测[J]. 林业工程学报, 2019, 4（1）: 115-120.
LIU Y, ZHOU X L, HU Z K, et al. Wood defect detection based on optimized convolutional neural network[J]. Journal of Forestry Engineering, 2019, 4（1）: 115-120.
[22] 王泽霞, 陈革, 陈振中. 基于改进卷积神经网络的化纤丝饼表面缺陷识别[J]. 纺织学报, 2020, 41（4）: 39-44.
WANG Z X, CHEN G, CHEN Z Z. Surface defect recognition of chemical fiber cake based on improved convolutional neural network[J]. Journal of Textile Research, 2020, 41（4）: 39-44.
[23] 王志中. 基于改进蚁群算法的移动机器人路径规划研究[J]. 机械设计与制造, 2018, 12（1）: 242-244.
WANG Z Z. Research on mobile robot path planning based on improved ant colony algorithm[J]. Mechanical Design and Manufacturing, 2018, 12（1）: 242-244.
[24] 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. Defect detection of jujube based on convolutional neural network of net in net[J]. Food & Machinery, 2020, 36（2）: 140-145, 181.
[25] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39（6）: 1 137-1 149.