Real-time accurate recognition algorithm for litchi fruit varieties based on improved YOLO11

HUANG Mingjie; CAI Weiqiang; ZHANG Zijian; FANG Zhanzhuo; GUO Weilun; LONG Yongbing; LAN Yubin; WANG Jianhua

doi:10.11975/j.issn.1002-6819.202412219

Transactions of the Chinese Society of Agricultural Engineering > 2025 > 41(11): 156-164. > DOI: 10.11975/j.issn.1002-6819.202412219

HUANG Mingjie, CAI Weiqiang, ZHANG Zijian, et al. Real-time accurate recognition algorithm for litchi fruit varieties based on improved YOLO11[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(11): 156-164. DOI: 10.11975/j.issn.1002-6819.202412219

Citation:

PDF (1292 KB)

Real-time accurate recognition algorithm for litchi fruit varieties based on improved YOLO11

1.
College of Electronic Engineering & College of Artificial Intelligence, South China Agricultural University, Guangzhou 510642, China
2.
National Center for International Collaboration Research on Precision Agricultural Aviation Pesticides, Spraying Technology (NPAAC), Guangzhou 510642, China

More Information

Received Date: December 28, 2024
Revised Date: May 05, 2025
Available Online: May 26, 2025

Graphical Abstract

Abstract

Abstract

Litchi is one of the most important fruits widely planted in southern China. However, manual identification cannot fully meet the large-scale production at present, due to the time-consuming and laborious. Particularly, Litchi is rich in a variety of resources, leading to the large similarity among varieties. Furthermore, the rapid and accurate identification of litchi varieties is often required in the process of intelligent production and sales. In this study, a recognition model (SCL-YOLO11) was proposed for the litchi fruit variety using improved YOLO11. Firstly, the C2f module (CSP2f, cross-stage partial fusion) of YOLO11model was added with the SIMAM attention mechanism to replace the original C2PSA module. Different feature dimensions of litchi images were focused to automatically adjust the features of each spatial position in the key areas; Secondly, CMUNeXt convolution with the large kernel and separable depth was applied to the C3k2 module, in order to improve the perception of the litchi geometric features under various occlusion. The experimental results show that the recognition accuracy of the improved SCL-YOLO11 model was 99.61%, which was improved by 27.10, 15.06, 12.47, 7.05, 4.83 and 2.89 percentage, respectively, compared with the VGG-19, VIT, AlexNet, ResNet-50, YOLOv8 and YOLO11 model. The parameter size of the model was 1.27 M, and the calculation was 3.1 G, which was reduced by 17.5% and 6.1%, respectively, compared with the YOLO11 model. The improved SCL-YOLO11 model was used to carry out real-time and accurate variety recognition for the litchi fruits with subtle texture differences and shape differences. The network scale was then reduced after data collection. Furthermore, the attention mechanism was fused with the C2f module. The weight of the SimAM attention mechanism was adjusted for the features of the C2f module after splicing. The enhanced features were outputted after segmentation. The accuracy and recall rate of the improved model were enhanced by 1.29% and 1.09%, respectively, compared with the original. In the convolution module, the CMUNeXt block with the large-core depth separable convolution was applied in the parallel convolution layer of the C3K2 module. The diverse geometric features of the litchi were then extracted to maintain the depth of the feature extraction in the C3K2 module. A series of tests were conducted to verify the improved SCL-YOLO11 model in the natural environment. The data sets were selected with different light intensity and occlusion conditions. The recognition accuracy of the SCL-YOLO11 model was 96.89%, 97.87%, and 98.48% under the conditions of insufficient illumination, strong light, and shadow, respectively; whereas the recognition accuracy of the SCL-YOLO11 model was 98.18% and 96.89% under the condition of the fruit and branch-leaf occlusion, respectively. There were better recognition accuracy and robustness, compared with the YOLOv8 and YOLO11. In a simulation, the reasoning time of the improved SCL-YOLO11 model was much less than that of the YOLOv8 and YOLO11 under different detection quantities. Especially when the detection quantity reached 1 000, the reasoning time was reduced by 43.82% and 2.9%, respectively, indicating higher accuracy than the rest. As such, both parameters and calculations were reduced for the real-time accuracy. The finding can provide the technical reference to develop intelligent equipment for the quality detection of litchi fruits.
- Litchi,
- YOLO11,
- image processing,
- deep learning,
- variety identification,
- lightweight

FullText(HTML)

References (32)

References

[1]	方壮东,范琴,彭远璇. 广东十大主推荔枝品种特性分析[J]. 中国果业信息,2024,41(9):96-101. DOI: 10.3969/j.issn.1673-1514.2024.09.074 FAMG Zhuangdong, FAN Qin, PENG Yuanxuan. Analysis of characteristics of top ten recommended litchi varieties in Guangdong province[J]. China Fruit Industry Information, 2024, 41(9): 96-101. (in Chinese with English abstract) DOI: 10.3969/j.issn.1673-1514.2024.09.074
[2]	CHEN J, KAO S H, HE H, et al. Run, don't walk: Chasing higher FLOPS for faster neural networks[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023: 12021-12031.
[3]	莫宇达,邹湘军,叶敏,等. 基于Sylvester方程变形的荔枝采摘机器人手眼标定方法[J]. 农业工程学报,2017,33(4):47-54. DOI: 10.11975/j.issn.1002-6819.2017.04.007 MO Yuda, ZOU Xiangjun, YE Min, et al. Hand-eye calibration method based on Sylvester equation deformation for lychee harvesting robot[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(4): 47-54. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.2017.04.007
[4]	LUO Y, CAI X, QI J, et al. FPGA–accelerated CNN for real- time plant disease identification[J]. Computers and Electronics in Agriculture, 2023, 207: 107715. DOI: 10.1016/j.compag.2023.107715
[5]	刘忠,卢安舸,崔浩,等. 基于改进 YOLOv8 的轻量化荷叶病虫害检测模型[J]. 农业工程学报,2024,40(19):1-9. LIU Zhong,LU Ange,CUI Hao,et al. A lightweight lotus leaf diseases and pests detection model using improved YOLOv8[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(19): 1-9. (in Chinese with English abstract).
[6]	张秀花,静茂凯,袁永伟,等. 基于改进 YOLOv3-Tiny 的番茄苗分级检测[J]. 农业工程学报,2022,38(1):221-229. DOI: 10.11975/j.issn.1002-6819.2022.01.025 ZHANG Xiuhua, JING Maokai, YUAN Yongwei, et al. Tomato seedling classification detection using improved YOLOv3-Tiny[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2022, 38(1): 221-229. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.2022.01.025
[7]	FU L, FENG Y, WU J, et al. Fast and accurate detection of kiwifruit in orchard using improved YOLOv3-tiny model[J]. Precision Agriculture, 2021, 22: 754-776. DOI: 10.1007/s11119-020-09754-y
[8]	刘洁,李燕,肖黎明,等. 基于改进YOLOv4模型的橙果识别与定位方法[J]. 农业工程学报,2022,38(12):173-182. DOI: 10.11975/j.issn.1002-6819.2022.12.020 LIU Jie, LI Yan, XIAO Liming, et al. Recognition and location method of orange based on improved YOLOv4 model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(12): 173-182. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.2022.12.020
[9]	周桂红,马帅,梁芳芳. 基于改进 YOLOv4 模型的全景图像苹果识别[J]. 农业工程学报,2022,38(21):159-168. DOI: 10.11975/j.issn.1002-6819.2022.21.019 ZHOU Guihong, MA Shuai, LIANG Fangfang. Recognition of the apple in panoramic images based on improved YOLOv4 model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(21): 159-168. (in Chinese with English abstract). DOI: 10.11975/j.issn.1002-6819.2022.21.019
[10]	WANG Z, JIN L, WANG S, et al. Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system[J]. Postharvest Biology and Technology, 2022, 185: 111808. DOI: 10.1016/j.postharvbio.2021.111808
[11]	张建华,孔繁涛,吴建寨,等. 基于改进VGG卷积神经网络的棉花病害识别模型[J]. 中国农业大学学报,2018,23(11):161-171. DOI: 10.11841/j.issn.1007-4333.2018.11.17 ZHANG Jianhua, KONG Fantao, WU Jianzhai, et al. Cotton disease recognition model based on improved VGG convolutional neural network[J]. Journal of China Agricultural University, 2018, 23(11): 161-171. (in Chinese with English abstract) DOI: 10.11841/j.issn.1007-4333.2018.11.17
[12]	YOU H, LU Y, TANG H. Plant disease classification and adversarial attack using SimAM-EfficientNet and GP-MI-FGSM[J]. Sustainability. 2023; 15(2): 1233.
[13]	傅隆生,冯亚利,ELKAMIL Tola,等. 基于卷积神经网络的田间多簇猕猴桃图像识别方法[J]. 农业工程学报,2018,34(2):205-211. DOI: 10.11975/j.issn.1002-6819.2018.02.028 FU Longsheng, FENG Yali, ELKAMIL Tola, et al. Image recognition method of multi-cluster kiwifruit in field based on convolutional neural networks[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(2): 205-211. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.2018.02.028
[14]	PAUL A, MACHAVARAM R, KUMAR D, et al. Smart solutions for capsicum harvesting: Unleashing the power of YOLO for detection, segmentation, growth stage classification, counting, and real-time mobile identification[J]. Computers and Electronics in Agriculture, 2024, 219: 108832. DOI: 10.1016/j.compag.2024.108832
[15]	XU W, WANG R. ALAD-YOLO: An lightweight and accurate detector for apple leaf diseases[J]. Frontiers in Plant Science, 2023, 14: 1204569. DOI: 10.3389/fpls.2023.1204569
[16]	XU L, DONG S, WEI H, et al. Defect signal intelligent recognition of weld radiographs based on YOLO V5-Improvement[J]. Journal of Manufacturing Processes, 2023, 99: 373-381. DOI: 10.1016/j.jmapro.2023.05.058
[17]	郑果,姜玉松,沈永林. 基于改进YOLOv7的水稻害虫识别方法[J]. 华中农业大学学报,2023,42(3):143-151. ZHENG Guo, JIANG Yusong, SHEN Yonglin. Rice pest identification method based on improved YOLOv7[J]. Journal of Huazhong Agricultural University, 2023, 42(3): 143-151. (in Chinese with English abstract)
[18]	李旭,刘青,匡敏球,等. 基于改进 YOLOX 的自然环境下辣椒果实检测方法[J]. 农业工程学报,2024,40(21):119-126. DOI: 10.11975/j.issn.1002-6819.202405175 LI Xu, LIU Qing, KUANG Minqiu, et al. Detecting chili pepper fruits in a natural environment using improved YOLOX[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(21): 119-126. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.202405175
[19]	GAO G, SHUAI C, WANG S. Mature tomato recognition and location algorithm based on binocular vision and deep learning[C]//International Conference on Artificial Intelligence, Virtual Reality and Visualization (AIVRV). Montreal, QC, Canada, 2023: 209-215.
[20]	LIU D, WANG L, SUN D, et al. Lychee variety discrimination by hyperspectral imaging coupled with multivariate classification[J]. Food Analytical Methods, 2014, 7(9): 1848-1857. DOI: 10.1007/s12161-014-9826-6
[21]	XIAO Y, WANG J , XIONG H, et al. Lychee cultivar fine-grained image classification method based on improved resnet-34 residual network[J], Journal of Agricultural Engineering, 2024, 93: 323-331.
[22]	周伟亮,王红军,邹湘军. 基于机器视觉的荔枝品质快速自动检测[J]. 中国农机化学报,2020,41(1):144-147,204. ZHOU Weiliang, WANG Hongjun, ZOU Xiangjun. Rapid automatic detection of lychee quality based on machine vision[J]. China Agricultural Machinery Chemistry Journal, 2020, 41(1): 144-147,204. (in Chinese with English abstract)
[23]	CHEN R, ZHOU H, XIE H, et al. YOLO-CE: An underwater low-visibility environment target detection algorithm based on YOLO11[J]. The Journal of Supercomputing, 2025, 81: 1-24.
[24]	殷慧军,王宝丽,景运革,等. 基于改进YOLOv7的无人机航拍视频西瓜计数方法[J]. 农业工程学报,2024,40(19):124-134. DOI: 10.11975/j.issn.1002-6819.202404070 YIN Huijun, WANG Baoli, JING Yunge, et al. Improved YOLOv7 method for counting watermelons in UAV aerial videos[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(19): 124-134. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.202404070
[25]	YANG L, ZHANG R Y, LIL, et al. SimAM: A simple, parameter-free attention module for convolutional neural networks[C]//International Conference on Machine Learning. PMLR, Vienna, Austria, 2021: 11863-11874.
[26]	LIANG L, ZHANG Y, ZHANG S, et al. Fast hyperspectral image classification combining transformers and SimAM-based CNNs[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-19.
[27]	HAN K, WANG Y, TIAN Q, et al. GhostNet: More features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, 2020: 1577-1586.
[28]	TANG F, DING J, QUAN Q, et al. Cmunext: An efficient medical image segmentation network based on large kernel and skip fusion[C]//2024 IEEE International Symposium on Biomedical Imaging (ISBI). IEEE, Athens, Greece, 2024: 1-5.
[29]	HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Montreal, QC, Canada. 2021: 13713-13722.
[30]	ZHANG Z, GUO W, ZHU S, et al. Toward arbitrary-oriented ship detection with rotated region proposal and discrimination networks[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(11): 1745-1749. DOI: 10.1109/LGRS.2018.2856921
[31]	CAO L, WANG Q, LUO Y, et al. YOLO-TSL: A lightweight target detection algorithm for UAV infrared images based on triplet attention and slim-nec [J].Infrared Physics & Technology, 2024, 141: 105487.
[32]	ZENG T, LI S, SONG Q, et al. Lightweight tomato real-time detection method based on improved YOLO and mobile deployment[J]. Computers and Electronics in Agriculture, 2023, 205: 107625. DOI: 10.1016/j.compag.2023.107625