Abstract
［Objective］ This study aims to address the problems of single methods,low efficiency,and high costs of the quality inspection of crayfish in industrial processing.［Methods］ A YOLO -HDR -based lightweight neural network model was proposed.The PP -HGNetv 2 model was employed to design a new YOLOv 8 backbone network,and the lightweight modules of HGstem and DWConv were introduced to reconstruct the network.The dynamic convolution block and other lightweight convolutions (GhostConv and RepConv ) in the official library were used to redesign the HGBlock of the new backbone network.The dynamic high -performance network modules (DynamicHGBlock,RepHGBlock,and GhostHGBlock ) were obtained to improve HGBlock and the feature expression of the network.The C2f module of the original neck network was improved by the repeated cross -stage local edge -preserving attention network RepNCSPELAN 4 to address the performance degradation caused by the lightweight network.［Results］］ The accuracy and average precision of the improved model reached 92.8% and 95.9%,respectively,which were 3.5% and 1.9% higher than those of the original model and better than those of other comparative target detection algorithms.The number of parameters and model size of the improved model were reduced by 17.7% and 16.2%,respectively,compared with those of the original YOLOv 8n model,and the amount of computation was reduced by 19.8%.［Conclusion］ The method established in this study demonstrates improved detection performance under the dense occlusion noise background,enabling the quality inspection of crayfish in industrial processing in the complex background before frozen packaging.
Publication Date
4-25-2025
First Page
100
Last Page
107
DOI
10.13652/j.spjx.1003.5788.2024.80598
Recommended Citation
Shuqing, WANG; Kaiyuan, CHEN; Miao, ZHOU; and Bogan, FAN
(2025)
"A method for detecting quality defects of crayfish based on YOLO-HDR,"
Food and Machinery: Vol. 41:
Iss.
3, Article 16.
DOI: 10.13652/j.spjx.1003.5788.2024.80598
Available at:
https://www.ifoodmm.cn/journal/vol41/iss3/16
References
[1] 于秀娟,郝向举,杨霖坤,等.中国小龙虾产业发展报告（2023） [J].中国水产,2023 (7):26-31.YU X J,HAO X J,YANG L K,et al.China crayfish industry development report (2023 ) [J].China Fisheries,2023 (7):26-31.
[2] SWAIN S,TRIPATHY A K.Automatic detection of potholes using VGG- 16 pre-trained network and Convolutional Neural Network [J].Heliyon,2024,10(10):e30957.
[3] CHEN S H,ZHU Z R,HOU X N.Classification of wafer map defect based on ResNeSt [J].Journal of Physics:Conference Series,2024,2 741(1):012019.
[4] KONG X H,LI X J,ZHU X X,et al.Detection model based on improved faster-RCNN in apple orchard environment [J].Intelligent Systems with Applications,2024,21: 200325.
[5] 王淑青,黄剑锋,张鹏飞,等.基于 YOLOv 4神经网络的小龙虾质量检测方法 [J].食品与机械,2021,37(3):120-124,194.WANG S Q,HUANG J F,ZHANG P F,et al.Crayfish quality detection method based on YOLOv 4[J].Food & Machinery,2021,37(3):120-124,194.
[6] 鲁濠,王淑青,鲁东林,等.基于改进 YOLOv 5的小龙虾品质检测方法 [J].湖北工业大学学报,2023,38(4):76-81.LU H,WANG S Q,LU D L,et al.Quality detection method of crayfish based on improved YOLOv 5[J].Journal of Hubei University of Technology,2023,38(4):76-81.
[7] ZHANG Y H,WEI C C,ZHONG Y,et al.Deep learning detection of shrimp freshness via smartphone pictures [J].Journal of Food Measurement and Characterization,2022,16(5):3 868-3 876.
[8] 高竟博,李晔,杜闯.基于深度学习的小龙虾分级算法 [J].现代计算机,2020 (26):40-46.GAO J B,LI Y,DU C.Crawfish classification algorithm based on deep learning [J].Modern Computer,2020 (26):40-46.
[9] 李小占,马本学,喻国威,等.基于深度学习与图像处理的哈密瓜表面缺陷检测 [J].农业工程学报,2021,37(1):223-232.LI X Z,MA B X,YU G W,et al.Surface defect detection of Hami melon using deep learning and image processing [J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(1):223-232.
[10] 陈斌,饶洪辉,王玉龙,等.基于 Faster-RCNN 的自然环境下油茶果检测研究 [J].江西农业学报,2021,33(1):67-70.CHEN B,RAO H H,WANG Y L,et al.Study on detection of Camellia fruit in natural environment based on Faster-RCNN[J].Acta Agriculturae Jiangxi,2021,33(1):67-70.
[11] ELBASSUONI S,GHATTAS H,EL ATI J,et al.Deep NOVA:a deep learning NOVA classifier for food images [J].IEEE Access,2022,10:128523.
[12] HELWAN A,SALLAM MA'AITAH M K,ABIYEV R H,et al.Deep learning based on residual networks for automatic sorting of bananas [J].Journal of Food Quality,2021,2 021:5516368.
[13] MUKHIDDINOV M,MUMINOV A,CHO J.Improved classification approach for fruits and vegetables freshness based on deep learning [J].Sensors,2022,22(21):8 192.
[14] MI Z W,ZHANG X D,SU J Y,et al.Wheat stripe rust grading by deep learning with attention mechanism and images from mobile devices [J].Frontiers in Plant Science,2020,11:558126.
[15] KAMILARIS A,PRENAFETA-BOLDÚ F X.Deep learning in agriculture:a survey [J].Computers and Electronics in Agriculture,2018,147:70-90.
[16] 滕文想,王成,费树辉,等.基于 HGTC-YOLOv 8n模型的煤矸识别算法研究 [J].工矿自动化,2024,50(5):52-59.TENG W X,WANG C,FEI S H,et al.Research on coal gangue recognition algorithm based on HGTC-YOLOv 8n model [J].Journal of Mine Automation,2024,50(5):52-59.
[17] WOO W M,ORO A E.SnapShot:hair follicle stem cells [J].Cell,2011,146(2):334.
[18] ZHANG P F,LO E,LU B T.High performance depthwise and pointwise convolutions on mobile devices [J].Computer Science,2020,34(4):6 795-6 802.
[19] HAN K,WANG Y H,GUO J Y,et al.ParameterNet:parameters are all you need for large-scale visual pretraining of mobile networks [C]// 2024 IEEE/CVF Conference on Computer Visionand Pattern Recognition (CVPR ).Seattle:IEEE,2024:15 751-15 761.
[20] CHEN Y P,DAI X Y,LIU M C,et al.Dynamic convolution:attention over convolution kernels [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Seattle:IEEE,2020:11 027-11 036.
[21] WANG C Y,YEH I H,MARK LIAO H Y.YOLOv 9:learning what you want to learn using programmable gradient information [C]// Computer Vision-ECCV 2024.Cham:Springer Nature Switzerland,2025:1-21.