Abstract
Objective: In order to improve the situation that existing fruit recognition and classification methods rely on manual operation and complex equipment. Methods: A lightweight model YOLO-FFD (YOLO with fruit and freshen detection) was proposed, which based on the YOLOv5 framework. Firstly, LightweightC3 was designed as the basic unit of the backbone feature extraction network based on the depth separable convolution and GELU activation function, which reduced the number of model parameters and computation, and speeds up the convergence of the model. Secondly, EnhancedC3, a large kernel depth separable convolution module, was used to improve the neck of the original model, suppressed information loss and enhance the feature fusion ability of the model, so as to improve the detection accuracy of the model. Finally, GSConv was used to replace the common convolution in the feature fusion network to further lighten the model. Results: The experimental results showed that the average accuracy of the proposed model reached 96.12%, the FPS on RTX 3090 was 172, and the speed on the embedded Jetson TX2 was 20 frames per second. Compared with the original YOLOv5 model, the mAP was improved by 2.21%, the calculation amount was reduced by 26%, and the speed was increased by two times. Conclusion: YOLO-FFD can meet the requirement of identifying fruit varieties and freshness, and improve the falsely detection and missing detection in complex scenes.
Publication Date
1-30-2024
First Page
115
Last Page
121
DOI
10.13652/j.spjx.1003.5788.2023.80432
Recommended Citation
Zi, YAN; Liangyan, CHEN; Weihua, LIU; Huaqing, LAI; and Sheng, YE
(2024)
"Fruit variety and freshness recognition method based on YOLO-FFD,"
Food and Machinery: Vol. 40:
Iss.
1, Article 17.
DOI: 10.13652/j.spjx.1003.5788.2023.80432
Available at:
https://www.ifoodmm.cn/journal/vol40/iss1/17
References
[1] ROCHA A, HAUAGGE D C, WAINER J, et al. Automatic fruit and vegetable classification from images[J]. Computers and Electronics in Agriculture, 2010, 70（1）: 96-104.
[2] DUBEY S R, JALAL A S. Fruit and vegetable recognition by fusing colour and texture features of the image using machine learning[J]. International Journal of Applied Pattern Recognition, 2015, 2（2）: 160-181.
[3] ZHANG Y D, DONG Z, CHEN X, et al. Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation[J]. Multimedia Tools and Applications, 2019, 78: 3 613-3 632.
[4] 刘禾, 汪懋华. 水果果形判别人工神经网络专家系统的研究[J]. 农业工程学报, 1996（1）: 171-176.
LIU H, WANG M H. Study on neural network expert system for fruit shape judgement[J].Transactions of the Chinese Society of Agricultural Engineering, 1996（1）: 171-176.
[5] SEMARY N, THARWAT A, EL-HARIRI E, et al. Fruit-based tomato grading system using features fusion and support vector machine[C]// Intelligent Systems' 2014. Warsaw: Springer, 2014: 401-410.
[6] MOALLEM P, SERAJODDIN A, POURGHASSEM H. Computer vision-based apple grading for golden delicious apples based on surface features[J]. Information Processing in Agriculture, 2017, 4（1）: 33-40.
[7] SUHARJITO, ELWIREHARDJA G N, PRAYOGA J S. Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches[J]. Computers and Electronics in Agriculture, 2021, 188: 106359.
[8] GAI R L, CHEN N, YUAN H. A detection algorithm for cherry fruits based on the improved YOLO-v4 model[J]. Neural Computing and Applications, 2023, 35（19）: 13 895-13 906.
[9] CHEN S M, XIONG J T, JIAO J M, et al. Citrus fruits maturity detection in natural environments based on convolutional neural networks and visual saliency map[J]. Precision Agriculture, 2022, 23（5）: 1 515-1 531.
[10] ANANTHANARAYANA T, PTUCHA R, KELLY S C. Deep learning based fruit freshness classification and detection with CMOS image sensors and edge processors[J]. Electronic Imaging, 2020, 32（12）: 172-177.
[11] 陈实. 轻量化改进的YOLOv5与道路病害实时检测[D]. 武汉: 武汉大学, 2023: 23.
CHEN S. Lightweight improved YOLOv5 and real-time detection of road damage[D]. Wuhan: Wuhan University, 2023: 23.
[12] 赵九霄, 张馨, 史凯丽, 等. 基于改进Tiny-YOLOv5l算法的串型番茄定位与计数[J]. 食品与机械, 2022, 38（12）: 79-86.
ZHAO J X, ZHANG X, SHI K L, et al. Localization and counting of string tomatoes based on improved Tiny-YOLOv5l algorithm[J]. Food & Machinery, 2022, 38（12）: 79-86.
[13] 梁秀满, 肖寒. 基于SDD-YOLO的轻量级带钢缺陷实时检测算法[J/OL]. 中国测试. （2023-01-10） [2023-05-13]. http://kns.cnki.net/kcms/detail/51.1714.TB.20230109.1648.002.html.
LIANG X M, XIAO H. Lightweight strip defect real-time detection algorithm based on SDD-YOLO[J]. China Measurement & Test:1-8. （2023-01-10） [2023-05-13]. http://kns.cnki.net/kcms/detail/51.1714.TB.20230109.1648.002.html.
[14] HOWARD A, SANDLER M, CHU G, et al. Searching for mobilenetv3[C]// Proceedings of the IEEE/CVF international conference on computer vision. Seoul: IEEE, 2019: 1 314-1 324.
[15] MA N, ZHANG X, ZHENG H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]// Proceedings of the European Conference on Computer Vision （ECCV）. Munich: Springer, 2018: 116-131.
[16] HAN K, WANG Y, TIAN Q, et al. Ghostnet: More features from cheap operations[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Seattle: IEEE, 2020: 1 580-1 589.
[17] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector[C]// Computer Vision-ECCV 2016. Amsterdam: Springer, 2016: 21-37.
[18] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 7 263-7 271.
[19] 王淑青, 黄剑锋, 张鹏飞, 等. 基于YOLOv4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.
WANG S Q, HUANG J F, ZHANG P F, et al. Crayfish quality detection method based on YOLOv4[J]. Food & Machinery, 2021, 37（3）: 120-124.