Abstract
［Objective ］ Efficiently identify eggs with defects on their appearance in the automatic production process.［Methods ］ Designed a detection model based on fusing Fasternet module and YOLOv 5s.The model used the Kmeans ++ algorithm to re -cluster the dataset and optimizeed the bounding box.The Bottleneck module in the C 3 structure was replaced by the Fasternet Block module to reduce the parameters and improve the percision in the process of detection.The Soft -NMS,a non -maximum suppression was utilized to improve the detection of eggs with similar features.The CBAM attention mechanism was introduced to enhance the function of extracting important features.［Results］ Compared with the YOLOv 5 original model,the experiment results showed that the mAP@ 0.5 and mAP@ 0.5:0.95 respectively had increased by 3.2% and 5.2%,respectively.The amount of calculation and parameters was reduced by 19.6% and 16.9%,respectively.Compared with YOLOv 7-tiny and YOLOv 8 models,the improved model has significant advantages.［Conclusion ］ The experimental method can optimize the detection percision and reduces the parameters in the detection of egg' appreance,so as to achieve the purpose of identifying defected eggs in the automatic production.Efficiently identify eggs with defects on their appearance in the automatic production process.
Publication Date
2-18-2025
First Page
105
Last Page
112,165
DOI
10.13652/j.spjx.1003.5788.2023.81137
Recommended Citation
Jingxin, WEI; Zhongju, CHEN; and Haoran, XU
(2025)
"Detection of egg appreance based on Fasternet and YOLOv 5 model,"
Food and Machinery: Vol. 40:
Iss.
8, Article 15.
DOI: 10.13652/j.spjx.1003.5788.2023.81137
Available at:
https://www.ifoodmm.cn/journal/vol40/iss8/15
References
[1] 庄珑昱,郑江霞.鸡蛋品质评价方法研究进展及其影响因素分析 [J].中国家禽,2024,46(3):87-94.ZHUANG L Y,ZHENG J X.Factors affecting the quality of eggs [J].China Poultry,2024,46(3):87-94.
[2] 佟平,臧凤,陈红兵,等.禽蛋蛋白质功能成分的抗氧化研究进展 [J].食品与生物技术学报,2023,42(4):16-23.TONG P,ZANG F,CHEN H B,et al.A comprehensive review on antioxidant activity of functional ingredients derived from egg proteins [J].Journal of Food Science and Biotechnology,2023,42(4):16-23.
[3] 褚素欣,任岩峰,姚慧敏,等.鸡蛋外观品质评价指标及在太行鸡蛋生产中的应用 [J].北方牧业,2022 (19):31-32.CHU S X,REN Y F,YAO H M,et al.Evaluation index of egg appearance quality and its application in Taihang egg production[J].Northern Animal Husbandry,2022 (19):31-32.
[4] 胥保文,孙力,蔡健荣,等.基于 DSP的鸡蛋裂纹多通道检测系统 [J].食品与机械,2018,34(10):130-132.XU B W,SUN L,CAI J R,et al.Multi channel detection system of eggshell crack based on DSP [J].Food & Machinery,2018,34(10):130-132.
[5] WANG H J,MAO J H,ZHANG J Y,et al.Acoustic feature extraction and optimization of crack detection for eggshell [J].Journal of Food Engineering,2016 (171):240-247.
[6] 李雅琪,孙力,陈诚,等.基于多维振动响应信号分析的鸡蛋裂纹检测研究 [J].镇江高专学报,2019,32(4):31-35.LI Y Q,SUN L,CHEN C,et al.A study of eggshell crack detection based on the analysis of multidimensional vibration signals [J].Journal of Zhenjiang College,2019,32(4):31-35.
[7] ARIVAZHAGAN S,SHEBIAH R N,SUDHARSAN H,et al.External and internal defect detection of egg using machine vision [J].Journal of Emerging Trends in Computing and Information Science,2013,4(3):257-261.
[8] 涂伟沪,蔡玲霞,李学军.基于改进蝗虫算法优化 Canny算子的 鸡 蛋 裂 纹 图 像 检 测 [J].食 品 与 机 械,2022,38(2):167-172,202.TU W H,CAI L X,LI X J.Egg crack image detection method based on improved grasshopper optimization algorithm and canny operator [J].Food & Machinery,2022,38(2):167-172,202.
[9] 张健,崔英杰.基于改进粒子群算法的鸡蛋裂纹检测方法 [J].食品与机械,2020,36(7):136-139,226.ZHANG J,CUI Y J.Egg crack detection based on improved particle swarm optimization [J].Food & Machinery,2020,36(7):136-139,226.
[10] 陈羽立,孙付春,郭兴华,等.基于 EfficientNet 的鸡蛋裂纹检测研究 [J].成都大学学报 (自然科学版 ),2020,39(4):385-389.CHEN Y L,SUN F C,GUO X H,et al.Research on egg crack detection based on EfficientNet [J].Journal of Chengdu University (Natural Science Edition ),2020,39(4):385-389.
[11] LIU C,WEN H Y,YIN G,et al.Research on intelligent recognition method of egg cracks based on efficientnet netork model [J].Journal of Physics:Conference Series,2023,2 560:012015.
[12] 赵祚喜,罗阳帆,黄杏彪,等.基于机器视觉和 YOLOv 4的破损鸡蛋在线检测研究 [J].现代农业装备,2022,43(1):8-16.ZHAO Z X,LUO Y F,HUANG X B,et al.Research on on -line detection of damaged eggs based on machine vision and YOLOv 4[J].Modern Agricultural Equipment,2022,43(1):8-16.
[13] 杨航,何皓明,李滕科,等.基于改进 YOLOv 5的鸽子蛋壳破损检测 [J].西南师范大学学报 (自然科学版 ),2023,48(8):92-102.YANG H,HE H M,LI T K,et al.Detection of pigeon eggshell breakage based on improved YOLOv 5[J].Journal of Southwest China Normal University (Natural Science Edition ),2023,48(8):92-102.
[14] 姚学峰,李超.改进的 YOLOv 5蛋类缺陷自动检测模型 [J].食品与机械,2022,38(11):155-159,183.YAO X F,LI C.An improved automatic detection model for egg defection based on YOLOv 5[J].Food & Machinery,2022,38(11):155-159,183.
[15] ZHU L L,GENG X,LI Z,et al.Improving YOLOv 5 with attention mechanism for detecting boulders from planetary images [J].Remote Sens -Basel,2021,13(18):3 776.
[16] 王宏,韩晨,袁伯阳,等.基于改进 YOLOv 5的拥挤行人检测算法 [J].科学技术与工程,2023,23(27):11 730-11 738.WANG H,HAN C,YUAN B Y,et al.Crowded pedestrian detection algorithm based on improved YOLOv 5[J].Science Technology and Engineering,2023,23(27):11 730-11 738.
[17] ARTHUR D,VASSILVITSKII S.K-means++:advantages of careful seeding [C]// Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms.New Orleans:ACM,2007:1 027-1 035.
[18] CHEN J R,KAO S H,HE H,et al.Run,don’t walk:chasing higher FLOPS for faster neural networks [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:12 021-12 031.
[19] BODLA N,SINGH B,CHELLAPPA R,et al.Soft-NMS:improving object detection with one line of code [C]// Proceedings of the IEEE International Conference on Computer Vision.Venice Italy:IEEE,2017:5 561-5 569.
[20] WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional block attention module [C]// Proceedings of the European Conference on Computer Vision (ECCV ).Munich:Springer,2018:3-19.
[21] LIN T Y,MAIRE M,BELONGIE J S,et al.Microsoft COCO:common objects in context [C]// European Conference on Computer Vision.Zurich:Springer,2014:740-755.
[22] 魏明军,陈钊,纪占林,等.一种基于 STI-YOLO的锌花背景干扰下带钢表面缺陷检测方法 [J].河南师范大学学报 (自然科学版 ),2023,51(4):84-92.WEI M J,CHEN Z,JI Z L,et al.A method for detecting surface defects of strip steel under the background interference of spangles based on STI -YOLO [J].Journal of Henan Normal University (Natural Science Edition ),2023,51(4):84-92.
[23] 乔琛,韩梦瑶,高苇,等.基于 Faster-NAM-YOLO的黄瓜霜霉病菌孢子检测 [J].农业机械学报,2023,54(12):288-299.QIAO C,HAN M Y,GAO W,et al.Quantitative detection of cucumber downy mildew spores at multi -scale based on Faster -NAM-YOLO [J].Transactions of the Chinese Society for Agricultural Machinery,2023,54(12):288-299.
[24] MA X,GUO F M,NIU W,et al.Pconv:the missing but desirable sparsity in DNN weight pruning for real -time execution on mobile devices [J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(4):5 117-5 124.
[25] ZHENG Z H,WANG P,LIU W,et al.Distance -iou loss:faster and better learning for bounding box regression [J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12 993-13 000.
[26] 程雪,范翠蝶,宁中华.雀斑蛋品质及其影响因素研究 [J].中国家禽,2019,41(19):6-9.CHENG X,FAN C D,NING Z H,et al.Quality of freckle eggs and its influencing factors [J].China Poultry,2019,41(19):6-9.
[27] 常利民,张洋,汪春明,等.鸡蛋、鸡肉及奶粉中 22种有机氯农药残留的测定 [J].食品与生物技术学报,2022,41(5):98-105.CHANG L M,ZHANG Y,WANG C M,et al.Determination of 22 organochlorine pesticides in egg,chicken and milk powder [J].Journal of Food Science and Biotechnology,2022,41(5):98-105.
[28] FANG M T,CHENZ J,PRZYSTUPA K,et al.Examination of abnormal behavior detection based on improved YOLOv 3[J].Electronics (Basel ),2021,10(2):197.
[29] WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv 7:trainable bag -of-freebies sets new state -of-the-art for real -time object detectors [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:7 464-7 475.
[30] HUSSAIN M.YOLO-v1 to YOLO -v8,the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection [J].Machines,2023,11(7):677.
[31] SELVARAJU R R,COGSWELL M,DAS A,et al.Grad-cam:visual explanations from deep networks via gradient -based localization [J].Int J Comput Vis,2020,128(2):336-359.
[32] 王猛,高树静,张俊虎,等.基于改进 YOLOv 5的安全绳目标检测 [J].计算机测量与控制,2024,32(6):42-50.WANG M,GAO S J,ZHANG J H,et al.Safe rope target detection based on improved YOLOv 5[J].Computer Measurement & Control,2024,32(6):42-50.
