Abstract
[Objective] To address the high missed detection rate of defective fruits and poor grading accuracy in current post-harvest fragrant pear sorting. [Methods] On the basis of an existing visual inspection system for fragrant pears, a machine vision detection system integrating an improved YOLOv8s algorithm and multi-dimensional morphological features is designed. An ECA attention module is introduced to enhance the model sensitivity to subtle defects, enabling fast and precise localization and segmentation of pears. Conventional morphological feature extraction is employed to conduct multi-dimensional shape analysis for identifying and rejecting defective fruits. Pressure-sensitive sensors are then used to grade the remaining qualified pears, realizing comprehensive quality screening and grading. [Results] The proposed system significantly reduces the missed detection rate and improves overall sorting efficiency. The improved YOLOv8s model achieves the single-target segmentation detection rate of 93.7%, the defect detection accuracy of 94.8%, and the grading accuracy of 97.8%. [Conclusion] The detection method integrating deep learning with machine vision effectively meets the practical requirements of post-harvest fragrant pear sorting.
Publication Date
7-13-2026
First Page
109
Last Page
115
DOI
10.13652/j.spjx.1003.5788.2025.81104
Recommended Citation
Jinkai, WANG; Chenchen, WU; Rouxin, CHENG; and Rentao, WU
(2026)
"A multi-defect detection system based on improved YOLOv 8s and morphological features for fragrant pear grading,"
Food and Machinery: Vol. 42:
Iss.
6, Article 14.
DOI: 10.13652/j.spjx.1003.5788.2025.81104
Available at:
https://www.ifoodmm.cn/journal/vol42/iss6/14
References
[1] 任越美,李垒,张军锋,等.融合改进 YOLOv 11与动态分拣策略的食品自动化分拣系统研究 [J].食品与机械,2025,41(9):82-90.REN Y M,LI L,ZHANG J F,et al.Food automated sorting system integrated with improved YOLOv 11 and dynamic sorting strategy [J].Food & Machinery,2025,41(9):82-90.
[2] 王宇航,曹洪武.计算机视觉技术在农业领域的应用 [J].现代农业科技,2024 (4):178-181.WANG Y,CAO H W.Application of computer vision technology in the field of agriculture [J].Modern Agricultural Science and Technology,2024 (4):178-181.
[3] 杨婷婷,郭志勋,雷定湘,等.机器视觉技术在农业中的应用[J].安徽农学通报,2021,27(18):110-111.YANG T T,GUO Z X,LEI D X,et al.Application of machine vision technology in agriculture [J].Anhui Agricultural Science Bulletin,2021,27(18):110-111.
[4] 郜梅贵.基于机器视觉的梨果实表型特征鉴定与分级方法研究[D].南京:南京农业大学,2022:1-72.GAO M G.Study on the characterization of phenotypic traits and grading method of pear fruit based on machine vision [D].Nanjing:Nanjing Agricultural University,2022:1-72.
[5] 郝明星.基于猕猴桃果皮颜色的分级方法及品质评价 [D].咸阳:西北农林科技大学,2025:1-54.HAO M X.A grading method based on the color of the kiwifruit skin and quality evaluation [D].Xianyang:Northwest A & F University,2025:1-54.
[6] 何婷婷,姚继超,张钟莉莉,等.基于图像局部方差的亮度矫正下番茄表面缺陷检测方法 [J].食品与机械,2023,39(9):128-133,161.HE T T,YAO J C,ZHANG Z L L,et al.Tomato surface defect detection method based on image local variance considering brightness correction [J].Food & Machinery,2023,39(9):128-133,161.
[7] 谭厚森,马文宏,田原,等.基于改进 YOLOv 8n的香梨目标检测方法 [J].农业工程学报,2024,40(11):178-185.TAN H S,MA W H,TIAN Y,et al.Improved YOLOv 8n object detection of fragrant pears [J].Transactions of the Chinese Society of Agricultural Engineering,2024,40(11):178-185.
[8] 赵 敏,范 英,高 思 伟,等.结 合 Swin-Transformer 的 改 进YOLOv 5s包装盒缺陷检测算法 [J].制造业自动化,2024,46(12):34-40.ZHAO M,FAN Y,GAO S W,et al.Improved YOLOv 5s packaging defect detection algorithm combined with swin-transformer [J].Manufacturing Automation,2024,46(12):34-40.
[9] 葛根波,吴陈陈,吴任涛,等.融合 YOLOv 8与形态学特征的马铃薯分级多缺陷检测系统 [J].粮油食品科技,2026,34(1):170-178.GE G B,WU C C,WU R T,et al.An integrated YOLOv 8 and morphological features-based system for multi-defect detection in potato grading [J].Science and Technology of Cereals,Oils and Foods,2026,34(1):170-178.
[10] 周韩莲,叶青,刘文祺.复杂背景下的轻量级遥感军用飞机目标检测 [J].光电工程,2025,52(2):240270.ZHOU H L,YE Q,LIU W Q.Lightweight remote sensing military aircraft target detection in complex backgrounds [J].Opto-Electronic Engineering,2025,52(2):240270.
[11] 陈漾,钟小勇,刘钱强.基于多尺度特征融合的遥感图像目标检测算法 [J].电光与控制,2025,32(8):45-52.CHEN Y,ZHONG X Y,LIU Q Q.An object detection algorithm based on multi-scale feature fusion for remote sensing image [J].Electronics Optics & Control,2025,32(8):45-52.
[12] WANG Q L,WU B G,ZHU P F,et al.ECA-net:efficient channel attention for deep convolutional neural networks [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Seattle,WA:IEEE,2020:11 531-11 539.
[13] 黄秀娟.基于 Sobel算子的板件钢材表面裂纹数字图像识别研究 [J].软件,2024,45(4):77-79.HUANG X J.Research on digital image recognition of surface cracks in plate steel based on sobel operator [J].Software,2024,45(4):77-79.
