Abstract
[Objective] To establish a nondestructive detection method for fruit appearance. [Methods] Nectarines were used as the research subject. The IQQU3 smart phone camera was used to capture the picture data, which was then preprocessed. The image annotation program Labelimg was used to label the data. Panning, left-right flipping, and mirror flipping were used to enlarge the data. Using an ratio of 8∶2, the enlarged photos were split into training and test sets. Lastly, the data was trained for 150 epochs using five YOLOv8 models （n, s, m, l, x）. The training results of the five models were compared and analyzed in order to determine which detection model was the best. [Results] The nectarine dataset was constructed, there were 4,205 total photos; YOLOv8 （n, s, m, l, x） the total loss values in the training set were 2.275, 1.778, 1.482, 1.880, and 1.401, respectively, The total loss values of the test set were 2.724, 2.253, 2.057, 2.105, and 2.004, respectively; YOLOv8 （n, s, m, l, x） precision were 94.0%, 98.0%, 97.4%, 97.3%, 97.9%, respectively, The recall were 95.4%, 95.5%, 95.9%, 96.9%, and 96.9%, respectively. In a comprehensive comparison YOLOv8s was the better model, and the average detection accuracy mAP_0.5 was 97.8%. The average precision of fresh, bruise and scar were 96.2%, 98.8% and 98.4%, respectively. The inference time and calculation amount （GFLOPs） were 179.4 ms and 28.4 respectively. [Conclusion] YOLOv8 can effectively detect the quality of fruit appearance, which can be used for non-destructive testing of fruit appearance, and this study can provide new ideas for non-destructive testing of fruits.
Publication Date
9-11-2024
First Page
103
Last Page
110
DOI
10.13652/j.spjx.1003.5788.2023.80836
Recommended Citation
Xingping, TANG; Baijuan, WANG; Hongxin, YANG; Zhengming, YANG; Rujia, LI; and Wendou, WU
(2024)
"Research on fruit appearance detection and classification method based on YOLOv8,"
Food and Machinery: Vol. 40:
Iss.
7, Article 16.
DOI: 10.13652/j.spjx.1003.5788.2023.80836
Available at:
https://www.ifoodmm.cn/journal/vol40/iss7/16
References
[1] 田有文, 吴伟, 卢时铅, 等. 深度学习在水果品质检测与分级分类中的应用[J]. 食品科学, 2021, 42（19）: 260-270.
TIAN Y W, WU W, LU S Q, et al. Application of deep learning in fruit quality detection and grading[J]. Food Science, 2021, 42（19）: 260-270.
[2] HE Y, XIAO Q L, BAI X L, et al. Recent progress of nondestructive techniques for fruits damage inspection: a review[J]. Critical Reviews in Food Science and Nutrition, Taylor & Francis, 2022, 62（20）: 5 476-5 494.
[3] 张杰, 夏春蕾, 张荣福, 等. 基于注意力机制的水果损伤检测及分类[J]. 光学仪器, 2023, 45（2）: 26-35.
ZHANG J, XIA C L, ZHANG R F, et al. Fruit damage detection and classification based on attention mechanism[J]. Optical Instruments, 2023, 45（2）: 26-35.
[4] RASHID A N A, AMIR F, RAMLAN S A, et al. Automated asian fruit grading system using stereo vision technique[J]. Journal of Physics: Conference Series, IOP Publishing, 2020, 1 535（1）: 012007.
[5] 周胜安, 黄耿生, 张译匀, 等. 基于深度学习的水果缺陷实时检测方法[J]. 食品与机械, 2021, 37（11）: 123-129.
ZHOU S A, HUANG G S, ZHANG Y Y, et al. Real-time detection method of fruit defects based on deep learning[J]. Food & Machinery, 2021, 37（11）: 123-129.
[6] 安小松. 基于机器视觉的外部缺陷柑橘在线分选方法研究[D]. 武汉: 华中农业大学, 2022: 14-18.
AN X S. Research on online sorting method of citrus with external defects based on machine vision[D]. Wuhan: Huazhong Agricultural University, 2022: 14-18.
[7] LIANG X T, JIA X Y, HUANG W Q, et al. Real-time grading of defect apples using semantic segmentation combination with a pruned YOLO V4 network[J]. Foods, Multidisciplinary Digital Publishing Institute, 2022, 11（19）: 3 150.
[8] CHEN X, ZHOU G X, CHEN A B, et al. The fruit classification algorithm based on the multi-optimization convolutional neural network[J]. Multimedia Tools and Applications, 2021, 80（7）: 11 313-11 330.
[9] DHIMAN P, KUKREJA V, MANOHARAN P, et al. Anovel deep learning model for detection of severity level of the disease in citrus fruits[J]. Electronics, Multidisciplinary Digital Publishing Institute, 2022, 11（3）: 495.
[10] NITHYA R, SANTHI B, MANIKANDAN R, et al. Computer vision system for mango fruit defect detection using deep convolutional neural network[J]. Foods, Multidisciplinary Digital Publishing Institute, 2022, 11（21）: 3 483.
[11] YANG G L, WANG J X, NIE Z L, et al. A lightweight YOLOv8 tomato detection algorithm combining feature enhancement and attention[J]. Agronomy, Multidisciplinary Digital Publishing Institute, 2023, 13（7）: 1 824.
[12] 麻宇轩. 基于深度学习的细粒度图像分类算法研究[D]. 北京: 北京印刷学院, 2023: 25-26.
MA Y X. Research on fine-grained image classification algorithm based on deep learning[D]. Beijing: Beijing Institute of Graphic Communication, 2023: 25-26.
[13] 熊恩杰, 张荣芬, 刘宇红, 等. 面向交通标志的Ghost-YOLOv8检测算法[J]. 计算机工程与应用, 2023, 59（20）: 200-207.
XIONG E J, ZHANG R F, LIU Y H, et al. Ghost-YOLOv8 detection algorithm for traffic signs[J]. Computer Engineering and Applications, 2023, 59（20）: 200-207.
[14] VEERAPPAN K, NATARAJAN S, CHUNG H, et al. Molecular insights of fruit quality traits in peaches, prunus persica[J]. Plants, Multidisciplinary Digital Publishing Institute, 2021, 10（10）: 2 191.
[15] ARANTES R B, VOGIATZIS G, FARIA D R. Learning an augmentation strategy for sparse datasets[J]. Image and Vision Computing, 2022, 117（1）: 104338.
[16] ZHOU S R, ZHANG J Q, JIANG H, et al. Data augmentation with Mobius transformations[J]. Machine Learning: Science and Technology, IOP Publishing, 2021, 2（2）: 025016.
[17] 孙书魁, 范菁, 孙中强, 等. 基于深度学习的图像数据增强研究综述[J]. 计算机科学, 2024, 51（1）: 150-167.
SUN S K, FAN J, SUN Z Q, et al. Survey of image data augmentation techniques for deep learning[J]. Computer Science, 2024, 51（1）: 150-167.
[18] 彭勇. 基于改进YOLO深度学习模型的烟支外观质量检测[D]. 昆明: 云南财经大学, 2023: 31-33.
PENG Y. Cigarette appearance quality detection based on improved YOLO deep learning model[D]. Kunming: Yunnan University of Finance and Economics, 2023: 31-33.
[19] 罗家梅, 王敏. 基于YOLOv5的水果品质检测与分类方法研究[J]. 软件导刊, 2023, 22（9）: 190-195.
LUO J M, WANG M. Research on fruit quality detection and classification method based on YOLOv5[J]. Software Guide, 2023, 22（9）: 190-195.
[20] DE MORAES J L, DE OLIVEIRA NETO J, BADUE C, et al. Yolo-papaya: a papaya fruit disease detector and classifier using CNNs and convolutional block attention modules[J]. Electronics, Multidisciplinary Digital Publishing Institute, 2023, 12（10）: 2 202.