Real time detection method of fruit defects based on deep learning

Authors

ZHOU Sheng-an, Guangdong Vocational Institute of Public Administration Electronic Information System, Guangzhou, Guangdong 510800, China
HUANG Geng-sheng, Guangdong Vocational Institute of Public Administration Electronic Information System, Guangzhou, Guangdong 510800, China
ZHANG Yi-yun, Guangdong Vocational Institute of Public Administration Electronic Information System, Guangzhou, Guangdong 510800, China
GAO Dong-fa, School of Computer Science, Guangdong University of Foreign Studies, Guangzhou, Guangdong 510665, China

Abstract

Objective: This study aimed to optimize and improve the CenterNet method for detecting fruit defects. Methods: the lightweight convolutional neural network of MobileNetV3 was used to replace the original backbone network of CenterNet accelerate the detection speed, improve the module of MobileNetV3, enhance the detection ability of the model for small and medium-sized defective blocks of fruit, and optimize the pre detection stage of CenterNet to increase its detection accuracy. Results: The recognition rate of significant defects such as apples with diameter > 4 mm was 99.7%, and the detection speed was 113 FPS, with the model volume of 1.31 MB. Conclusion: Compared with models CenterNet _ Resnet18 and CenterNet_Shuffler, model MO-CenterNet has better balance in training time, detection speed and accuracy.

Publication Date

11-28-2021

First Page

123

Last Page

129

DOI

10.13652/j.issn.1003-5788.2021.11.022

Recommended Citation

Sheng-an, ZHOU; Geng-sheng, HUANG; Yi-yun, ZHANG; and Dong-fa, GAO (2021) "Real time detection method of fruit defects based on deep learning," Food and Machinery: Vol. 37: Iss. 11, Article 22.
DOI: 10.13652/j.issn.1003-5788.2021.11.022
Available at: https://www.ifoodmm.cn/journal/vol37/iss11/22

References

[1] 周伟亮, 王红军, 邹湘军. 基于机器视觉的荔枝品质快速自动检测[J]. 中国农机化学报, 2020, 41（1）: 144-147, 204.
[2] 左兴健, 武广伟. 猕猴桃自动分级设备设计与试验[J]. 农业机械学报, 2014, 45（S1）: 287-295.
[3] 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.
[4] 李红娟, 杨颖辉. 基于混沌多宇宙算法的苹果表面缺陷检测研究[J]. 江苏农业科技, 2017, 45（15）: 202-205.
[5] 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）: 125-148.
[6] 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.
[7] 夏雪, 孙琦鑫, 侍啸, 等. 基于轻量级无锚点深度卷积神经网络的树上苹果检测模型[J]. 智慧农业（中英文）, 2020（1）: 99-110.
[8] SANDLER M, HOWARD A, ZHU Meng-long, et al. MobileNetV2: Inverted residuals and linear bottlenecks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake: IEEE, 2018: 4 510-4 520.
[9] BAO Wen-xia, YANG Ya-ping, LIANG Dong, et al. Multi-residual module stacked hourglass networks for human pose estimation[J]. Journal of Beijing Institute of Technology, 2020, 29（1）: 110-119.
[10] REN Shao-qing, HE Kai-ming, GRISHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39（6）: 1 137-1 149.
[11] HE K, GKIOXARI G, DOLLR P, et al. Mask R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice: Computer Society, 2017: 2980-298.
[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified,real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 779-788.
[13] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]// European Conference on Computer Vision. Springer, Cham: IEEE, 2016: 21-37.
[14] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 99: 2 999-3 007.
[15] DUAN K, BAI S, XIE L, et al. Centernet: Keypoint triplets for object detection[J/OL]. arXiv. （2019-04-19）[2021-07-08]. https://arxiv.org/abs/1904.08189.
[16] ZHOU Xing-yi, WANG De-quan, KRAHENBUHL P. Objects as points[J/OL]. arXiv. （2019-04-25）[2021-07-08]. https://arxiv.org/abs/1904.07850v2.
[17] XIAO Bin, WU Hai-ping, WEI Yi-chen. Simple baselines for human pose estimation and tracking[J]. European Conference on Computer Vision: Springer, 2018: 472-487.
[18] HE Kai-ming, ZHANG Xiang-yu, REN Shao-qing, et al. Deep residual learning for image recognition[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[19] SANDLER M, HOWARD A, ZHU M, et al. Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmenta-tion[C]// The IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4 510-4 520.
[20] HOWARD A, SANDLER M, CHU G, et al. Searching for mobilenetv3[C]// Proceedings of the IEEE International Conference on Computer Vision. Seoul: [s.n.], 2019: 1 314-1 324.