Abstract
Objective: Improve the detection accuracy and efficiency of apple surface defects. Methods: An detection method for apple surface defects was established based on an improved convolutional neural network (CNN) and data augmentation method. Firstly, the classical CNN was improved to detect apple surface defects. Then, using the conditional generation adversarial network, the image data of surface defect free and defective apples was augmented with synthetic apple images to improve the detection performance of the improved CNN for apple surface defects. Finally, by pruning the CNN model, the detection accuracy, detection speed and energy saving limits of apple surface defects were balanced reasonably to improve the practicability of the proposed method. Results: When 2 048 interpretive neurons were selected in the interpretation layer of the improved CNN, the average detection accuracy was the highest among the interpretive neuron number situations. Additionally, the diversity of the apple image data sets was enhanced with the synthetic apple images produced by the conditional generation adversarial network. In addition, the accuracy of the proposed method for detecting apple surface defects increased continuously with the increase of the proportion of the enhanced images in the test data set. When the ratio of the pruned model size to the original model size decreased from 100% to 50%, the detection efficiency of apple surface defects was doubled with 6.96% detection accuracy decreasing. Conclusion: This method is expected to realize the automatic defect detection in apple production and processing, and provide a reference for the developing of other fruit surface defect detection methods.
Publication Date
10-20-2023
First Page
122
Last Page
128,226
DOI
10.13652/j.spjx.1003.5788.2023.60043
Recommended Citation
Wei, PI; Xilong, QU; Shaocheng, WANG; and Qingchun, LI
(2023)
"Apple surface defect detection based on improved CNN and data augmentation,"
Food and Machinery: Vol. 39:
Iss.
8, Article 19.
DOI: 10.13652/j.spjx.1003.5788.2023.60043
Available at:
https://www.ifoodmm.cn/journal/vol39/iss8/19
References
[1] 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 fusion of infrared and visible images[J]. Food & Machinery, 2021, 37（12）: 127-131.
[2] 王迎超, 张婧婧, 达新民, 等. 基于K-means与KNN的多特征苹果在线分级[J]. 新疆农业科学, 2023, 60（3）: 643-650.
WANG Y C, ZHANG J J, DA X M, et al. Design of multi-feature apple online grading system based on K-means and KNN[J]. Xinjiang Agricultural Sciences, 2023, 60（3）: 643-650.
[3] CHEN S H, LAI Y W, KUO C L, et al. A surface defect detection system for golden diamond pineapple based on CycleGAN and YOLOv4[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34（10）: 8 041-8 053.
[4] 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 light weight convolutional neural network[J]. Hebei Journal of Industrial Science and Technology, 2021, 38（5）: 388-394.
[5] LIANG X, JIA X, HUANG W, et al. Real-time grading of defect apples using semantic segmentation combination with a pruned YOLOV4 network[J]. Foods, 2022, 11（19）: 3 150.
[6] 张军锋, 尚展垒. 基于深度学习卷积神经网络的花生籽粒完整性检测[J]. 食品与机械, 2022, 38（5）: 24-29, 36.
ZHANG J F, SHANG Z L. Peanut kernel integrity detection based on deep learning convolution neural network[J]. Food & Machinery, 2022, 38（5）: 24-29, 36.
[7] 魏冉, 裴悦琨, 姜艳超, 等. 基于改进Faster R-CNN模型的樱桃缺陷检测[J]. 食品与机械, 2021, 37（10）: 98-105, 201.
WEI R, PEI Y K, JIANG Y C, et al. Detection of cherry defects based on improved faster R-CNN model[J]. Food & Machinery, 2021, 37（10）: 98-105, 201.
[8] 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. Defect detection method of apples based on GoogLeNet deep transfer learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51（7）: 30-35.
[9] 高辉, 马国峰, 刘伟杰. 基于机器视觉的苹果缺陷快速检测方法研究[J]. 食品与机械, 2020, 36（10）: 125-129, 148.
GAO H, MA G T, LIU W J. Research on a rapid detection of apple detects based on mechanical vision[J]. Food & Machinery, 2020, 36（10）: 125-129, 148.
[10] FAN S, LIANG X, HUANG W, et al. Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network[J]. Computers and Electronics in Agriculture, 2022, 193: 106715.
[11] TULBURE A,ALECANDRU T A, DULF E H. A review on modern defect detection models using DCNNs-Deep convolutional neural networks[J]. Journal of Advanced Research, 2022, 35: 33-48.
[12] HE Y, XIAO Q, BAI X, et al. Recent progress of nondestructive techniques for fruits damage inspection: A review[J]. Critical Reviews in Food Science and Nutrition, 2022, 62（20）: 5 476-5 494.
[13] 黄霖, 吴亮, 高胜严, 等. 基于生成对抗网络的无目标深度检索哈希攻击算法[J]. 计算机学报, 2023, 46（4）: 803-813.
HUANG L, WU L, GAO S Y, et al. GAN-based untargeted attack on deep hashing for image retrieval[J]. Chinese Journal of Computers, 2023, 46（4）: 803-813.
[14] 朱晓慧, 钱丽萍, 傅伟. 基于GAN的网络安全数据扩充研究综述与展望[J]. 计算机应用与软件, 2022, 39（11）: 288-296.
ZHU X H, QIAN L P, FU W. Review and prospect of data augmentation in network security based on GAN[J]. Computer Applications and Software, 2022, 39（11）: 288-296.
[15] AGGARWAL A, MITTAL M, BATTINENI G. Generative adversarial network: An overview of theory and applications[J]. International Journal of Information Management Data Insights, 2021, 1（1）: 100004.
[16] 李钰, 杨道勇, 刘玲亚, 等. 利用生成对抗网络实现水下图像增强[J]. 上海交通大学学报, 2022, 56（2）: 134-142.
LI Y, YANG D Y, LIU L Y, et al. Underwater image enhancement based on generative adversarial networks[J]. Journal of Shanghai Jiaotong University, 2022, 56（2）: 134-142.
[17] NIU M Y, ZLOKAPA A, BROUGHTON M, et al. Entangling quantum generative adversarial networks[J]. Physical Review Letters, 2022, 128（22）: 220505.
[18] SAXENA D, CAO J. Generative adversarial networks （GANs） challenges, solutions, and future directions[J]. ACM Computing Surveys （CSUR）, 2021, 54（3）: 1-42.
[19] ALQHTANI H, KAVAKLI-THORNE M, KUMAR G. Applications of generative adversarial networks （gans）: An updated review[J]. Archives of Computational Methods in Engineering, 2021, 28: 525-552.
[20] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint, 2015: 1511.06434.