Surface Defect Detection of Frozen Dumplings Based on Improved RetinaNet Model

FEI Zhigen; GUO Xing; SONG Xiaoxiao; LU Hao; ZHAO Xinchang

doi:10.13386/j.issn1002-0306.2024040041

Volume 46 Issue 6

Mar. 2025

Turn off MathJax

Article Contents

Abstract

References

Science and Technology of Food Industry > 2025 > 46(6): 9-19. > DOI: 10.13386/j.issn1002-0306.2024040041

FEI Zhigen, GUO Xing, SONG Xiaoxiao, et al. Surface Defect Detection of Frozen Dumplings Based on Improved RetinaNet Model[J]. Science and Technology of Food Industry, 2025, 46(6): 9−19. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2024040041.

Citation:

PDF (24422 KB)

Surface Defect Detection of Frozen Dumplings Based on Improved RetinaNet Model

Henan Key Laboratory of Intelligent Manufacturing of Machinery and Equipment, School of Mechanical and Electrical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China

More Information

Received Date: April 02, 2024
Available Online: January 06, 2025

Graphical Abstract

Abstract

Abstract

Objective: To improve the accuracy of surface defect detection of quick-frozen dumplings. Methods: A dataset covering five quick-frozen dumpling forms (normal, leak, half, broken and adhesion) was elaborated, and the GX-RetinaNet network model was proposed for surface defect detection and localization of quick-frozen dumplings. The model was improved based on the RetinaNet network. The backbone feature extraction network adopted the ResNeXt-50 model, which had strong feature extraction ability. The addition of the convolutional block attention module (CBAM) and the use of the Swish activation function could effectively suppress the influence of background noise. By adding the path aggregation network (PAN) structure behind the feature pyramid networks (FPN) structure to form a bidirectional feature fusion module, the fusion ability of target multi-scale feature information could be improved. Results: The online detection accuracy of the GX-RetinaNet network for surface defects of quick-frozen dumplings under industrial field conditions was better than that of several mainstream target detection networks. The mAP was 94.8%, the Recall was 77.0% and the F1-score was 84.9%. Compared with the RetinaNet network, mAP, Recall, and F1-score increased by 2.6%, 2.6% and 2.4%, respectively. Conclusion: The GX-RetinaNet network model could meet the requirements of surface defect detection accuracy of quick-frozen dumplings. This study provided a feasible method for the application of deep learning theory in the surface defect detection of frozen dumplings.

FullText(HTML)

References (36)

References

[1]	李桂玉, 许秀峰. 影响速冻水饺冻裂因素分析及改进措施[J]. 食品科技,2004,30(3):46−47. [LI G Y, XU X F. Factors of deep-frozen dumpling crackle analysis and prevention[J]. Food Science and Technology,2004,30(3):46−47.] doi: 10.3969/j.issn.1005-9989.2004.03.016 LI G Y, XU X F. Factors of deep-frozen dumpling crackle analysis and prevention[J]. Food Science and Technology, 2004, 30（3）: 46−47. doi: 10.3969/j.issn.1005-9989.2004.03.016
[2]	梁灵, 张正茂, 张艳东, 等. 大豆蛋白对速冻水饺质量的影响[J]. 西北农林科技大学学报(自然科学版),2006,71(10):153−158. [LIANG L, ZHANG Z M, ZHANG Y D, et al. Effect of soybean protein on the quality of the frozen dumpling[J]. Journal of Northwest Sci-Tech University of Agriculture and Forestry(Natural Science Edition),2006,71(10):153−158.] doi: 10.3321/j.issn:1671-9387.2006.10.031 LIANG L, ZHANG Z M, ZHANG Y D, et al. Effect of soybean protein on the quality of the frozen dumpling[J]. Journal of Northwest Sci-Tech University of Agriculture and Forestry（Natural Science Edition）, 2006, 71（10）: 153−158. doi: 10.3321/j.issn:1671-9387.2006.10.031
[3]	YANG F, KIM Y. Application of yuba film as frozen dumpling wrappers[J]. LWT - Food Science & Technology,2021,151(7):112245.
[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 lightweight convolutional neural network[J]. Hebei Industrial Science and Technology,2021,38(5):388−394.] doi: 10.7535/hbgykj.2021yx05006 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 Science and Technology, 2021, 38（5）: 388−394. doi: 10.7535/hbgykj.2021yx05006
[5]	LI Y D, XUE J X, WANG K, et al. Surface defect detection of fresh-cut cauliflowers based on convolutional neural network with transfer learning[J]. Foods,2022,11(18):2915. doi: 10.3390/foods11182915
[6]	贾鹤鸣, 郎春博, 姜子超. 基于轻量级卷积神经网络的植物叶片病害识别方法[J]. 计算机应用,2021,41(6):1812−1819. [JIA H M, LANG C B, JIANG Z C. Plant leaf disease identification method based on lightweight convolutional neural network[J]. Journal of Computer Applications,2021,41(6):1812−1819.] doi: 10.11772/j.issn.1001-9081.2020091471 JIA H M, LANG C B, JIANG Z C. Plant leaf disease identification method based on lightweight convolutional neural network[J]. Journal of Computer Applications, 2021, 41（6）: 1812−1819. doi: 10.11772/j.issn.1001-9081.2020091471
[7]	刘一阳, 马子领. 基于机器学习的速冻水饺缺陷检测[J]. 现代计算机, 2023, 29(24):1−9, 39. [LIU Y Y, MA Z L. Defect detection of quick-frozen dumplings based on Machine learning[J]. Modern Computer, 2019, 29(24):1−9, 39.] LIU Y Y, MA Z L. Defect detection of quick-frozen dumplings based on Machine learning[J]. Modern Computer, 2019, 29（24）: 1−9, 39.
[8]	周春欣, 霍怡之, 杜有海, 等. 基于改进的RetinaNet大豆外观品质无损检测[J]. 中国粮油学报,2024,39(9):172−180. [ZHOU C X, HUO Y Z, DU Y H, et al. Nondestructive testing of soybean appearance quality based on improved RetinaNet[J]. Chinese Journal of Cereals and Oils,2024,39(9):172−180.] ZHOU C X, HUO Y Z, DU Y H, et al. Nondestructive testing of soybean appearance quality based on improved RetinaNet[J]. Chinese Journal of Cereals and Oils, 2024, 39（9）: 172−180.
[9]	李培婷. 基于深度学习的速冻水饺表面缺陷检测算法研究[D]. 郑州:郑州轻工业大学, 2023. [LI P T. Research on surface defect detection algorithm of quick-frozen dumplings based on deep learning[D]. Zhengzhou:Zhengzhou University of Light Industry, 2023.] LI P T. Research on surface defect detection algorithm of quick-frozen dumplings based on deep learning[D]. Zhengzhou: Zhengzhou University of Light Industry, 2023.
[10]	LI Y, WANG H N, FANG Y Q, et al. Learning power Gaussian modeling loss for dense rotated object detection in remote sensing images[J]. Chinese Journal of Aeronautics,2023,36(10):353−365. doi: 10.1016/j.cja.2023.04.022
[11]	张银萍, 徐燕, 朱双杰, 等. 基于机器视觉的金丝皇菊智能分级系统研究[J]. 食品工业科技,2022,43(5):13−20. [ZHANG Y P, XU Y, ZHU S J, et al. Research on intelligent grading system of golden silk chrysanthemum based on machine vision[J]. Science and Technology of Food Industry,2022,43(5):13−20.] ZHANG Y P, XU Y, ZHU S J, et al. Research on intelligent grading system of golden silk chrysanthemum based on machine vision[J]. Science and Technology of Food Industry, 2022, 43（5）: 13−20.
[12]	BAE W, YOO J, YE J C. Beyond deep residual learning for image restoration:persistent homology-guided manifold simplification[J]. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu, HI, USA:2017:1141−1149.
[13]	GONG Y Q, YU X H, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]// 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA:2021:1159−1167.
[14]	YOGESH, DUBEY A K, RATAN R, et al. Computer vision based analysis and detection of defects in fruits causes due to nutrients deficiency[J]. Cluster Computing, 2020, 23(1):1817–1826.
[15]	张志刚, 余鹏飞, 李海燕, 等. 基于多尺度特征引导的细粒度野生菌图像识别[J]. 激光与光电子学进展,2022,59(12):10. [ZHANG Z G, YU P F, LI H Y, et al. Fine-grained wild mushroom image recognition based on multi-scale feature guidance[J]. Advances in Laser and Optoelectronics,2022,59(12):10.] ZHANG Z G, YU P F, LI H Y, et al. Fine-grained wild mushroom image recognition based on multi-scale feature guidance[J]. Advances in Laser and Optoelectronics, 2022, 59（12）: 10.
[16]	BAO W X, FAN T, HU G S, et al. Detection and identification of tea leaf diseases based on AX-RetinaNet[J]. Scientific Reports,2022,12(1):1−16. doi: 10.1038/s41598-021-99269-x
[17]	TIAN Z, SHEN C H, CHEN H, et al. FCOS:A simple and strong anchor-free object detector[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020:1922−1933.
[18]	金山峰, 王冬欣, 黄俊仕, 等. 基于计算机视觉的茶叶品质在线评价系统[J]. 食品工业科技,2021,42(14):219−225. [JIN S F, WANG D X, HUANG J S, et al. Online evaluation system for tea quality based on computer vision[J]. Science and Technology of Food Industry,2021,42(14):219−225.] JIN S F, WANG D X, HUANG J S, et al. Online evaluation system for tea quality based on computer vision[J]. Science and Technology of Food Industry, 2021, 42（14）: 219−225.
[19]	刘海文, 郑元林, 钟崇军, 等. 基于改进YOLOv5l的印刷品缺陷检测[J]. 激光与光电子学进展,2019,61(10):228−235. [LIU H W, ZHENG Y L, ZHONG C J, et al. Print defect detection based on improved YOLOv5l[J]. Advances in Laser and Optoelectronics,2019,61(10):228−235.] LIU H W, ZHENG Y L, ZHONG C J, et al. Print defect detection based on improved YOLOv5l[J]. Advances in Laser and Optoelectronics, 2019, 61（10）: 228−235.
[20]	李雪露, 储茂祥, 杨永辉, 等. 基于CR-RFPR101的钢板表面缺陷检测[J]. 合肥工业大学学报(自然科学版),2023,46(12):1651−1658. [LI X L, CHU M X, YANG Y H, et al. Surface defect detection of steel plate based on CR-RFPR101[J]. Journal of Hefei University of Technology (Natural Science Edition),2023,46(12):1651−1658.] doi: 10.3969/j.issn.1003-5060.2023.12.010 LI X L, CHU M X, YANG Y H, et al. Surface defect detection of steel plate based on CR-RFPR101[J]. Journal of Hefei University of Technology （Natural Science Edition）, 2023, 46（12）: 1651−1658. doi: 10.3969/j.issn.1003-5060.2023.12.010
[21]	TETILA E, MACHADO B B, ASTOLFI G, et al. Detection and classification of soybean pests using deep learning with UAV images[J]. Computers and Electronics in Agriculture,2020,179(1):105836.
[22]	TAN L, HUANGFU T R, WU L Y, et al. Comparison of RetinaNet, SSD, and YOLO v3 for real-time pill identification[J]. BMC Medical Informatics and Decision Making,2021,21(1):1−11. doi: 10.1186/s12911-020-01362-0
[23]	YANG J F, FU X Y, HU Y W, et al. PanNet:A deep network architecture for Pan-Sharpening[J]. 2017 IEEE International Conference on Computer Vision (ICCV), 2017:1753−1761.
[24]	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[J] 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017:936−944.
[25]	ZHANG J, KARKEE M, ZHANG Q, et al. Multi-class object detection using faster R-CNN and estimation of shaking locations for automated shake-and-catch apple harvesting[J]. Computers and Electronics in Agriculture, 2020:173.
[26]	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. in IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011−2023. doi: 10.1109/TPAMI.2019.2913372
[27]	裴悦琨, 刘敬宇. 基于改进YOLOX模型的樱桃缺陷及分级检测方法[J]. 食品与机械,2023,39(1):7. [PEI Y K, LIU J Y. Cherry defect and grading detection method based on improved YOLOX model[J]. Food and Machinery,2023,39(1):7.] PEI Y K, LIU J Y. Cherry defect and grading detection method based on improved YOLOX model[J]. Food and Machinery, 2023, 39（1）: 7.
[28]	CAO L, YANG J Y, RONG Z W, et al. A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening[J]. Medical Image Analysis,2021,73(4):102197.
[29]	WOO S, PARK J, LEE J Y, et al. CBAM:Convolutional block attention module[J]. Lecture Notes in Computer Science, 2018:3–19.
[30]	ZHANG Z, LU Y Z, LU R F. Development and evaluation of an apple infield grading and sorting system[J]. Postharvest Biology and Technology,2021,180:111588. doi: 10.1016/j.postharvbio.2021.111588
[31]	谢安国, 纪思媛, 李月玲, 等. 基于遗传算法和深度神经网络的近红外高光谱检测猪肉新鲜度[J]. 食品工业科技,2024,45(17):1−7. [XIE A G, JI S Y, LI Y L, et al. Detection of pork freshness using NIR hyperspectral Imaging based on genetic algorithm and deep neural network[J]. Science and Technology of Food Industry,2024,45(17):1−7.] XIE A G, JI S Y, LI Y L, et al. Detection of pork freshness using NIR hyperspectral Imaging based on genetic algorithm and deep neural network[J]. Science and Technology of Food Industry, 2024, 45（17）: 1−7.
[32]	章曙光, 张文韬, 刘洋, 等. 改进MobileNet-SSD的电梯内电动车识别方法[J]. 机械设计与制造,2024(9):340−345. [ZHANG S G, ZHANG W T, LIU Y, et al. Improving the identification method of electric vehicles in elevators with MobileNet-SSD[J]. Mechanical Design and Manufacturing,2024(9):340−345.] doi: 10.3969/j.issn.1001-3997.2024.09.065 ZHANG S G, ZHANG W T, LIU Y, et al. Improving the identification method of electric vehicles in elevators with MobileNet-SSD[J]. Mechanical Design and Manufacturing, 2024（9）: 340−345. doi: 10.3969/j.issn.1001-3997.2024.09.065
[33]	ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5:Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Canada:Montreal, BC, 2021:2778−2788.
[34]	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4:Optimal speed and accuracy of object detection[J]. In ArXiv, 2020:2004.10934.
[35]	CHEN X, GUPTA A. An implementation of Faster RCNN with study for region sampling[J]. In ArXiv, 2017:1702.02138.
[36]	DING R W, DAI L H, LI G P, et al. TDD-Net:A Tiny defect detection network for printed circuit boards[J]. CAAI Transactions on Intelligence Technology,2019,4(2):110−116. doi: 10.1049/trit.2019.0019

Supplements (0)

Get Citation

PDF

XML

Article Metrics

Article views (39) PDF downloads (9)

Science and Technology of Food Industry

Surface Defect Detection of Frozen Dumplings Based on Improved RetinaNet Model

Abstract

References

Catalog

Article Metrics

Export File

Citation

Format

Content