Cherry defect and classification detection based on improved YOLOX model

Authors

LIU Jing-yu, Beidou High Precision Positioning Service Technology Engineering Laboratory of Liaoning Province, Dalian University, Dalian, Liaoning 116622, China; Environment Sensing and Intelligent Control Key Laboratory of Dalian, Dalian University, Dalian, Liaoning 116622, China
PEI Yue-kun, Beidou High Precision Positioning Service Technology Engineering Laboratory of Liaoning Province, Dalian University, Dalian, Liaoning 116622, China; Environment Sensing and Intelligent Control Key Laboratory of Dalian, Dalian University, Dalian, Liaoning 116622, ChinaFollow
CHANG Zhi-yuan, Beidou High Precision Positioning Service Technology Engineering Laboratory of Liaoning Province, Dalian University, Dalian, Liaoning 116622, China; Environment Sensing and Intelligent Control Key Laboratory of Dalian, Dalian University, Dalian, Liaoning 116622, China
CHAI Zhi, Beidou High Precision Positioning Service Technology Engineering Laboratory of Liaoning Province, Dalian University, Dalian, Liaoning 116622, China; Environment Sensing and Intelligent Control Key Laboratory of Dalian, Dalian University, Dalian, Liaoning 116622, China
CAO Pei-pei, Beidou High Precision Positioning Service Technology Engineering Laboratory of Liaoning Province, Dalian University, Dalian, Liaoning 116622, China; Environment Sensing and Intelligent Control Key Laboratory of Dalian, Dalian University, Dalian, Liaoning 116622, China

Corresponding Author(s)

裴悦琨（1985—），男，大连大学讲师，研究生导师，博士。E-mail：peiyuekun@126.com

Abstract

Objective: In order to expand the scope of cherry sales and achieve rapid grading of cherries under industrial conditions. Methods: Firstly, the YOLOX network was used to detect the defective fruit, in order to solve some problems where the defect was not obvious. The detection accuracy of the inconspicuous defect was improved by setting the appropriate fusion factor for the feature pyramid network, and in order to solve the problem of imbalance between various types of real samples, Focal Loss was integrated into the loss function. Then, the intact fruit was graded using the YOLOX network, and the attention mechanism CBAM was introduced to enhance the network feature extraction. Results: Experimental results showed that 97.59% of the mAP detected for cherry surface defects and 95.92% of the mAP of size and color grading. Conclusion: The accuracy of cherry defects and grading has been significantly improved by the improved YOLOX network.

Publication Date

4-25-2023

First Page

139

Last Page

145

DOI

10.13652/j.spjx.1003.5788.2022.80300

Recommended Citation

Jing-yu, LIU; Yue-kun, PEI; Zhi-yuan, CHANG; Zhi, CHAI; and Pei-pei, CAO (2023) "Cherry defect and classification detection based on improved YOLOX model," Food and Machinery: Vol. 39: Iss. 1, Article 23.
DOI: 10.13652/j.spjx.1003.5788.2022.80300
Available at: https://www.ifoodmm.cn/journal/vol39/iss1/23

References

[1] 王维, 刘东琴, 王佩. 果品分级检测技术的研究现状及发展[J]. 包装与食品机械, 2016, 34（6）: 55-58.
[2] HUSSAIN H N M, NASHAT A A. New effective techniques for automatic detection and classification of external olive fruits defects based on image processing techniques[J]. Multidimensional Systems and Signal Processing, 2019, 30（2）: 571-589.
[3] ZHANG W, HU J, ZHOU G, et al. Detection of apple defects based on the FCM-NPGA and a multivariate image analysis[J]. IEEE Access, 2020, 8: 38 833-38 845.
[4] DUBEY A K, RATAN R, ROCHA A. Computer vision based analysis and detection of defects in fruits causes due to nutrients deficiency[J]. Cluster Computing, 2020, 23（3）: 1 817-1 826.
[5] HU G, ZHANG E, ZHOU J, et al. Infield apple detection and grading based on multi-feature fusion[J]. Horticulturae, 2021, 7（9）: 276.
[6] KONDO N. Automation on fruit and vegetable grading system and food traceability[J]. Trends in Food Science & Technology, 2010, 21（3）: 145-152.
[7] WAN S, GOUDOS S. Faster R-CNN for multi-class fruit detection using a robotic vision system[J]. Computer Networks, 2020, 168: 107036.
[8] 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.
[9] ZHANG Z, LU Y, LU R. Development and evaluation of an apple infield grading and sorting system[J]. Postharvest Biology and Technology, 2021, 180: 111588.
[10] BARGOTI S, UNDERWOOD J. Deep fruit detection in orchards[C]// 2017 IEEE International Conference on Robotics and Automation （ICRA）. Singapore: Nstitute of Electrical and Electronics Engineering, 2017: 3 626-3 633.
[11] 梁鸿, 王庆玮, 张千, 等. 小目标检测技术研究综述[J]. 计算机工程与应用, 2021, 57（1）: 17-28.
[12] LIU Z, WANG S. Broken corn detection based on an adjusted YOLO with focal loss[J]. IEEE Access, 2019, 7: 68 281-68 289.
[13] GE Z, LIU S, WANG F, et al. Yolox: Exceeding yolo series in 2021[J]. arXiv preprint arXiv, 2021: 2107.08430.
[14] FU H, SONG G, WANG Y. Improved YOLOv4 marine target detection combined with CBAM[J]. Symmetry, 2021, 13（4）: 623.
[15] 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.
[16] LIN T Y, DOLLR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: Institute of Electrical and Electronics Engineering, 2017: 2 117-2 125.
[17] 刘博文. 基于深度学习的复杂场景中行人检测研究[D]. 广州: 广东工业大学, 2020: 33-36.
[18] GONG Y, YU X, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa: Institute of Electrical and Electronics Engineering, 2021: 1 160-1 168.
[19] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv, 2020: 2004.10934.
[20] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. advances in Neural Information Processing Systems, 2015, 28: 1506.01497.
[21] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]// European Conference on Computer Vision. [s.l.]: Springer Cham, 2016: 21-37.