MSL-Net: a lightweight apple leaf disease detection model based on multi-scale feature fusion

Abstract

Aiming at the problem of low detection accuracy due to the different scale sizes of apple leaf disease spots and their similarity to the background, this paper proposes a multi-scale lightweight network (MSL-Net). Firstly, a multiplexed aggregated feature extraction network is proposed using residual bottleneck block (RES-Bottleneck) and middle partial-convolution (MP-Conv) to capture multi-scale spatial features and enhance focus on disease features for better differentiation between disease targets and background information. Secondly, a lightweight feature fusion network is designed using scale-fuse concatenation (SF-Cat) and triple-scale sequence feature fusion (TSSF) module to merge multi-scale feature maps comprehensively. Depthwise convolution (DWConv) and GhostNet lighten the network, while the cross stage partial bottleneck with 3 convolutions ghost-normalization attention module (C3-GN) reduces missed detections by suppressing irrelevant background information. Finally, soft non-maximum suppression (Soft-NMS) is used in the post-processing stage to improve the problem of misdetection of dense disease sites. The results show that the MSL-Net improves mean average precision at intersection over union of 0.5 (mAP@0.5) by 2.0% over the baseline you only look once version 5s (YOLOv5s) and reduces parameters by 44%, reducing computation by 27%, outperforming other state-of-the-art (SOTA) models overall. This method also shows excellent performance compared to the latest research.

Keywords

A

References

[1] Zhong Y, Zhao M. Research on deep learning in apple leaf disease recognition. Computers and electronics in agriculture, 2020, 168: 105146 J]

[2] Zhang C L, Zhang S W, Yang J C, et al.. Apple leaf disease identification using genetic algorithm and correlation based feature selection method. International journal of agricultural and biological engineering, 2017, 10(2): 74-83[J]

[3] Pallathadka H, Ravipati P, Sajja G S, et al.. Application of machine learning techniques in rice leaf disease detection. Materials today: proceedings, 2022, 51: 2277-2280[J]

[4] Chakraborty S, Paul S, Raha-Uz-Zaman M. Prediction of apple leaf diseases using multiclass support vector machine. 2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques, January 5–7, 2021, DHAKA, Bangladesh, 2021, New York, IEEE147-151[C]

[5] Ren S Q, He K, Girshick R, et al.. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(06): 1137-1149 J]

[6] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08) [2024-01-23]. https://arxiv.org/abs/1804.02767.

[7] GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. (2021-08-06) [2023-01-22]. https//arxiv.org/abs/2107.08430.

[8] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 17–24, 2023, Vancouver, BC, Canada, 2023, New York, IEEE74647475[C]

[9] Liu W, Anguelov D, Erhan D, et al.. SSD: single shot multibox detector. 14th European Conference on Computer Vision, October 11–14, 2016, Amsterdam, Netherlands, 2016, Heidelberg, Cham Springer International Publishing2137[C]

[10] Zhu R, Zou H, Li Z, et al.. Apple-Net: a model based on improved YOLOv5 to detect the apple leaf diseases. Plants, 2022, 12(1): 169 J]

[11] Rehman Z U, Khan M A. Recognizing apple leaf diseases using a novel parallel real-time processing framework based on mask RCNN and transfer learning: an application for smart agriculture. IET image processing, 2021, 15(102157-2168 J]

[12] Zhang Y, Zhou G, Chen A, et al.. A precise apple leaf diseases detection using BCTNet under unconstrained environments. Computers and electronics in agriculture, 2023, 212: 108132 J]

[13] Sun H, Xu H, Liu B, et al.. MEAN-SSD: a novel real-time detector for apple leaf diseases using improved light-weight convolutional neural networks. Computers and electronics in agriculture, 2021, 189: 106379 J]

[14] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–22, 2018, Salt Lake City, UT, USA, 2018, New York, IEEE7132-7141[C]

[15] Chen J, Kao S, He H, et al.. Run, don’t walk: chasing higher FLOPs for faster neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–22, 2023, Vancouver, BC, Canada, 2023, New York, IEEE12341242[C]

[16] LIU Y, SHAO Z, TENG Y, et al. NAM: normalization-based attention module[EB/OL]. (2021-11-24) [2024-01-23]. https://arxiv.org/abs/2111.12419v1.

[17] Bodla N, Singh B, Chellappa R, et al.. Soft-NMS—improving object detection with one line of code. Proceedings of the IEEE International Conference on Computer Vision, October 22–29, 2017, Venice, Italy, 2017, New York, IEEE55625570[C]

[18] Yang Q, Duan S, Wang L. Efficient identification of apple leaf diseases in the wild using convolutional neural networks. Agronomy, 2022, 12(11): 2784 J]

[19] Selvaraju R R, Cogswell M, Das A, et al.. Grad-CAM: visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, October 22–29, 2017, Venice, Italy, 2017, New York, IEEE618-626[C]

RIGHTS & PERMISSIONS

Tianjin University of Technology