Abstract
[Objective] To improve the accuracy of apple defect identification and classification. [Methods] An apple defect identification method based on improved YOLOv 7-tiny is proposed. Firstly, a multi-angle image acquisition system is designed to sample and enhance the surface of the apple. Then, the YOLOv 7-tiny network is used to extract the features of the apple. The extracted features are dimensionally reduced and compressed with the improved fuzzy C-means clustering (IFCM) algorithm. Finally, the improved coati optimization algorithm (ICOA) is adopted to automatically optimize the hyperparameters of the YOLOv 7 model. The proposed method is compared with other methods, such as ResNet +FPN, YOLOv 5s, and PP-YOLOE, in terms of apple defect identification and classification performance under different resolutions and batch sizes. [Results] When the sample resolution is 224 pixels ×224 pixels, the proposed method achieves the detection accuracy of 98.6% and the recall rate of 97.9% and takes only about 50 ms to detect a single image on average, outperforming the other methods. [Conclusion] This system has high precision and real-time performance and can effectively improve the classification efficiency and quality of apples, which is of great engineering significance for the automatic sorting of fruits.
Publication Date
9-25-2025
First Page
100
Last Page
108
DOI
10.13652/j.spjx.1003.5788.2025.60032
Recommended Citation
Jun, LI; Botao, CAO; and Xindong, PENG
(2025)
"An apple defect identification method based on improved YOLOv 7-tiny,"
Food and Machinery: Vol. 41:
Iss.
8, Article 14.
DOI: 10.13652/j.spjx.1003.5788.2025.60032
Available at:
https://www.ifoodmm.cn/journal/vol41/iss8/14
References
[1] 郭德超,饶远立,张豪,等.结合机器视觉和光谱技术的番茄综合品质检测方法 [J].食品与机械,2024,40(9):123-130.GUO D C,RAO Y L,ZHANG H,et al.Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques [J].Food & Machinery,2024,40(9):123-130.
[2] 秦寅初,李涛,李旭,等.基于机器视觉的苹果表损智能检测系统设计 [J].食品与机械,2024,40(6):138-142.QIN Y C,LI T,LI X,et al.Design of apple damage automatic detection system based on machine vision [J].Food & Machinery,2024,40(6):138-142.
[3] 惠永永,赵春雨,宋昭漾,等.基于 BiFPN和Triplet注意力机制的 YOLOv 5s缺陷苹果识别算法 [J].华南农业大学学报,2025,46(3):419-428.HUI Y Y,ZHAO C Y,SONG Z Y,et al.A YOLOv 5s algorithm based on BiFPN and Triplet attention mechanism for identifing defective apple [J].Journal of South China Agricultural University,2025,46(3):419-428.
[4] 鄢紫,陈良艳,刘卫华,等.基于 YOLO-FFD 的水果品种和新鲜度识别方法 [J].食品与机械,2024,40(1):115-121.YAN Z,CHEN L Y,LIU W H,et al.Fruit variety and freshness recognition method based on YOLO-FFD [J].Food & Machinery,2024,40(1):115-121.
[5] 丁世春,马瑞峻,陈瑜.基于高光谱成像的水果品质检测研究进展 [J].江苏农业科学,2024,52(15):16-26.DING S C,MA R J,CHEN Y.Research progress on fruit quality detection based on hyperspectral imaging [J].Jiangsu Agricultural Sciences,2024,52(15):16-26.
[6] 陈娃蕊,陈娃迪,涂志刚,等.基于高精度机器视觉的柑橘智能分级与包装协同技术研究 [J].塑料包装,2024,34(6):9-14.CHEN W R,CHEN W D,TU Z G,et al.Research on intelligent grading and packaging collaborative technology of citrus based on high precision machine vision [J].Plastics Packaging,2024,34(6):9-14.
[7] 贾雪莹,赵春江,周娟,等.基于改进 YOLOv 7模型的柑橘表面缺陷在线检测 [J].农业工程学报,2023,39(23):142-151.JIA X Y,ZHAO C J,ZHOU J,et al.Online detection of citrus surface defects using improved YOLOv 7 modeling [J].Transactions of the Chinese Society of Agricultural Engineering,2023,39(23):142-151.
[8] GAO X T,LI S W,SU X T,et al.Application of advanced deep learning models for efficient apple defect detection and quality grading in agricultural production [J].Agriculture,2024,14(7):1 098.
[9] 谭涛,冯树南,温青纯,等.高光谱成像技术在水果品质检测中的应用研究进展 [J].江苏农业科学,2024,52(6):11-18.TAN T,FENG S N,WEN Q C,et al.Research progress on application of hyperspectral imaging technology in detection of fruit quality [J].Jiangsu Agricultural Sciences,2024,52(6):11-18.
[10] AKTER T,FAQEERZADA M A,KIM Y,et al.Hyperspectral imaging with multivariate analysis for detection of exterior flaws for quality evaluation of apples and pears [J].Postharvest Biology and Technology,2025,223:113453.
[11] HAN B,ZHANG J J,ALMODFER R,et al.Research on innovative apple grading technology driven by intelligent vision and machine learning [J].Foods,2025,14(2):258.
[12] ZHAO Z P,YIN C K,GUO Z L,et al.Research on apple recognition and localization method based on deep learning [J].Agronomy,2025,15(2):413.
[13] 王启航,顾寄南,蒋兴宇,等.基于改进 YOLOv 7-tiny的茶叶嫩芽识别方法 [J].中国农机化学报,2025,46(6):150-155.WANG Q H,GU J N,JIANG X Y,et al.Tea bud identification method based on improved YOLOv 7-tiny [J].Journal of Chinese Agricultural Mechanization,2025,46(6):150-155.
[14] LYU Z W,WANG Y,HUANG C L,et al.Dynamic monitoring and counting for lotus flowers and seedpods with UAV based on improved YOLOv 7-tiny [J].Computers and Electronics in Agriculture,2024,225:109344.
[15] 王淑青,陈开元,周淼,等.基于 YOLO-HDR 的小龙虾缺陷品质检测方法 [J].食品与机械,2025,41(3):100-107.WANG S Q,CHEN K Y,ZHOU M,et al.A method for detecting quality defects of crayfish based on YOLO-HDR [J].Food & Machinery,2025,41(3):100-107.
[16] 张妮,杨阿庆,韩立锋.多源异构数据模糊 C均值聚类挖掘方法仿真 [J].计算机仿真,2025,42(4):347-351.ZHANG N,YANG A Q,HAN L F,et al.Simulation of fuzzy C-means clustering mining method for multi-source heterogeneous data[J].Computer Simulation,2025,42(4):347-351.
[17] 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,et al.Egg crack image detection method based on improved grasshopper optimization algorithm and canny operator [J].Food & Machinery,2022,38(2):167-172,202.
[18] 姜宏维,程雨,段志.基于 K均值 +Davies-Bouldin 指数 +PCA法的桥梁结构性能综合评估算法研究 [J].公路,2024,69(4):124-132.JIANG H W,CHENG Y,DUAN Z.Research on comprehensive assessment algorithm of bridge structural performance based on K-means+Davies-Bouldin Index+PCA method [J].Highway,2024,69(4):124-132.
[19] 蒋金伟,杨启志,刘进福,等.基于改进浣熊优化算法的食品分拣机器人机械臂时间最优轨迹规划 [J].食品与机械,2025,41(3):81-87.JIANG J W,YANG Q Z,LIU J F,et al.Time-optimal trajectory planning for food sorting robot arms based on improved coati optimization algorithm [J].Food & Machinery,2025,41(3):81-87.
[20] LUO M,LIU M C,ZHANG S W,et al.Mining soil heavy metal inversion based on levy flight cauchy gaussian perturbation sparrow search algorithm support vector regression (LSSA-SVR ) [J].Ecotoxicology and Environmental Safety,2024,287:117295.