基于局部特征和视觉词袋模型的大豆叶片病害识别

doi:10.13733/j.jcam.issn.2095‑5553.2024.08.029

摘要/Abstract

摘要： 病害检测对提高大豆作物产量至关重要。针对传统视觉法诊断大豆作物病害而导致病害识别效率和分类准确率不高的问题，提出一种基于局部描述符和视觉词袋技术以数据表征大豆叶片图像的分类算法，同时保留有关潜在疾病的视觉信息。采用SIFT、DSIFT、PHOW和SURF 4种算法对大豆叶片的霜霉病、锈病TAN和锈病RB进行分类识别。结果表明，局部描述符PHOW表现出最佳的分类识别结果，其正确分类率为96.25%。进一步研究PHOW在不同颜色空间下的大豆病害识别效果。结果表明，与灰度图像相比，使用HSV、Opponent颜色空间可有效提升对大豆叶片病害检测的正确分类率，其正确分类率分别可达99.83%和99.58%，验证采用局部描述符和视觉词袋技术识别大豆叶片病害方法的可行性和高效性，并为其他作物的病害识别提供一种通用的分类识别方法。

关键词: 大豆叶片, 病害识别, 局部描述符, 视觉词袋, 颜色空间

Abstract: Disease detection is crucial for improving soybean crop yields. In response to the low efficiency and accuracy of disease recognition and classification caused by traditional visual diagnosis methods for soybean crop diseases, a classification algorithm based on local descriptors and visual bag‑of‑words techniques was proposed to represent soybean leaf images, while preserving visual information about potential diseases. Four algorithms such as SIFT, DSIFT, PHOW, and SURF, were employed to classify and recognize soybean leaf diseases such as downy mildew, rust TAN, and rust RB. The results demonstrated that the local descriptor PHOW yielded the best classification and recognition results, with an accuracy rate of 96.25%. Further research on the recognition effects of PHOW in different color spaces revealed that, compared to grayscale images, the use of HSV and Opponent color spaces could effectively improve the correct classification rate of soybean leaf disease detection, reaching accuracy rates of 99.83% and 99.58% respectively. This validates the feasibility and efficiency of identifying soybean leaf diseases by using local descriptors and visual bag‑of‑words techniques , and provides a general classification and recognition method for the disease recognition of other crops.

Key words: soybean leaf, disease identification, local descriptors, visual bag of words, color space

中图分类号:

郑金松, 谷海红, 蒋庆刚, 赵靖杰, 王贤, 韩增光. 基于局部特征和视觉词袋模型的大豆叶片病害识别[J]. 中国农机化学报, 2024, 45(8): 204-209.

Zheng Jinsong, Gu Haihong, Jiang Qinggang, Zhao Jingjie, Wang Xian, Han Zengguang. Identification of soybean leaf disease based on local features and visual bag of words model[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(8): 204-209.

参考文献

[ 1 ] 孙鹏，陈桂芬，曹丽英. 基于注意力卷积神经网络的大豆害虫图像识别[J]. 中国农机化学报， 2020， 41(2): 171-176.
Sun Peng， Chen Guifen， Cao Liying. Image recognition of soybean pests based on attention convolutional neural network [J]. Journal of Chinese Agricultural Mechanization， 2020， 41(2): 171-176.
[ 2 ] Saponari M， Manjunath K， Yokomi R K. Quantitative detection of Citrus tristeza virus in citrus and aphids by real‑time reverse transcription‑PCR (TaqMan) [J]. Journal of Virological Methods， 2008， 147(1): 43-53.
[ 3 ] 尚增强，杨东福，马质璞. 基于深度卷积神经网络的大豆叶片多种病害分类识别[J]. 大豆科学， 2021， 40(5): 662-668.
Shang Zengqiang， Yang Dongfu， Ma Zhipu. Automatic identification of soybean leaf diseases based on UAV image and deep convolution neural network [J]. Soybean Science， 2021， 40(5): 662-668.
[ 4 ] Gui J， Hao L， Zhang Q， et al. A new method for soybean leaf disease detection based on modified salient regions [J]. International Journal of Multimedia and Ubiquitous Engineering， 2015， 10(6): 45-52.
[ 5 ] Shrivastava S， Hooda D S. Automatic brown spot and frog eye detection from the image captured in the field [J]. American Journal of Intelligent Systems， 2014， 4(4): 131-134.
[ 6 ] 高莎，袁希平，甘淑，等. 集成SIFT算法与检测模型优化的UAV影像匹配方法[J]. 光谱学与光谱分析， 2022， 42(5): 1497-1503.
Gao Sha， Yuan Xiping， Gan Shu， et al. UAV image matching method integrating SIFT algorithm and detection model optimization [J]. Spectroscopy and Spectral Analysis， 2022， 42(5): 1497-1503.
[ 7 ] Liu Y， Yu D， Chen X， et al. TOP-SIFT: The selected SIFT descriptor based on dictionary learning [J]. The Visual Computer， 2019， 35: 667-677.
[ 8 ] Su D， Wu J， Cui Z， et al. CGCI-SIFT: A more efficient and compact representation of local descriptor [J]. Measurement Science Review， 2013， 13(3): 132-141.
[ 9 ] 刘颖，倪天宇，王富平，等. 融合局部聚合描述符和全局特征的现勘图像分类算法[J]. 科学技术与工程， 2020， 20(3): 1118-1124.
Liu Ying， Ni Tianyu， Wang Fuping， et al. Crime scene investigation image classification algorithm fusing VLAD and global features [J]. Science Technology and Engineering， 2020， 20(3): 1118-1124.
[10] Tu S， Xue Y， Zheng C， et al. Detection of passion fruits and maturity classification using Red‑Green‑Blue Depth images [J]. Biosystems Engineering， 2018， 175: 156-167.
[11] Cui Y， Chen A， Yang B， et al. Human visual perception‑based multi‑exposure fusion image quality assessment [J]. Symmetry， 2019， 11(12): 1494.
[12] Bay H， Ess A， Tuytelaars T， et al. Speeded‑up robust features (SURF) [J]. Computer Vision & Image Understanding， 2008， 110(3): 346-359.
[13] Fernandez C I， Leblon B， Wang J， et al. Detecting infected cucumber plants with close‑range multispectral imagery [J]. Remote Sensing， 2021， 13(15): 2948.
[14] Phan H， Ahmad A， Saraswat D. Identification of foliar disease regions on corn leaves using SLIC segmentation and deep learning under uniform background and field conditions [J]. IEEE Access， 2022， 10: 111985-111995.
[15] 翟玉婷，迟卫，金良安，等. 采用塔式关键词直方图的舰船图像实时分类检测方法[J]. 科学技术与工程， 2017， 17(33): 131-135.
Zhuo Yuting， Chi Wei， Jin Liang’an， et al. Real‑time detection method based on PHOW for ship images classification features [J]. Science Technology and Engineering， 2017， 17(33): 131-135.
[16] Mansourian L， Abdullah M T， Abdullah L N， et al. An effective fusion model for image retrieval [J]. Multimedia Tools and Applications， 2018， 77(13): 16131-16154.
[17] Banerji S， Sinha A， Liu C. New image descriptors based on color， texture， shape， and wavelets for object and scene image classification [J]. Neurocomputing， 2013， 117: 173-185.
[18] 刘靖. 基于局部聚合描述符的视点不变视觉位置识别[J]. 计算机工程与设计， 2020， 41(11): 3181-3187.
Liu Jing. View‑invariant visual position recognition based on vector of locally aggregated descriptors [J]. Computer Engineering and Design， 2020， 41(11): 3181-3187.
[19] 姚艺，黄卫华，章政，等. 基于改进SIFT的无人机双目目标识别与定位[J]. 组合机床与自动化加工技术， 2022(6): 49-53.
Yao Yi， Huang Weihua， Zhang Zheng， et al. UAV binocular vision target recognition and positioning based on improved SIFT algorithm [J]. Modular Machine Tool & Automatic Manufacturing Technique， 2022(6): 49-53.
[20] Liu Z Y， Wu H F， Huang J F. Application of neural networks to discriminate fungal infection levels in rice panicles using hyperspectral reflectance and principal components analysis [J]. Computers and Electronics in Agriculture， 2010， 72(2): 99-106.

[1]	张继成, 黄向党. 基于改进YOLOv3的玉米病害识别方法[J]. 中国农机化学报, 2024, 45(7): 269-275.
[2]	邱畅, 田光兆, 赵嘉威, 谢尚杰, 郑奎. 基于改进YOLOv5的草莓病害识别[J]. 中国农机化学报, 2024, 45(3): 198-204.
[3]	黄铭森, 张波, 李洪昌, 梁振伟, 黄涛, 任天成. 基于深度相机的水稻穗层高度检测研究[J]. 中国农机化学报, 2024, 45(1): 177-182.
[4]	梁万杰, 曹静, 孙传亮, 曹宏鑫, 张文宇, . 基于深度学习的农作物病害识别系统研发[J]. 中国农机化学报, 2023, 44(9): 169-175.
[5]	刘敏, 周丽. 基于多尺度特征融合网络的苹果病害叶片检测[J]. 中国农机化学报, 2023, 44(8): 184-190.
[6]	余胜, 谢莉. 基于迁移学习和卷积视觉转换器的农作物病害识别研究[J]. 中国农机化学报, 2023, 44(8): 191-197.
[7]	阮承治, 林根深, 陈旭, 孙月平, 杨君, 赵德安. 基于图像处理的蟹塘水草图像导航线拟合方法[J]. 中国农机化学报, 2023, 44(7): 147-153.
[8]	吴俊鹏, 黄光文, 李君, . 水果病害视觉与光谱检测技术研究现状及展望[J]. 中国农机化学报, 2023, 44(2): 112-118.
[9]	何雨霜, 王琢, 王湘平, 肖进, 罗友谊, 张俊峰. 深度学习在农作物病害图像识别中的研究进展[J]. 中国农机化学报, 2023, 44(2): 148-155.
[10]	阮承治, 陈茜, 陈旭, 赵升云, 孙月平, 赵德安. 颜色空间直方图相交法的竹条色差分类检测系统研究[J]. 中国农机化学报, 2022, 43(5): 85-92.
[11]	董萍, 卫梦华, 时雷, 郭伟. 迁移学习在玉米叶片病害识别中的研究与应用[J]. 中国农机化学报, 2022, 43(3): 146-152.
[12]	卫雅娜, 王志彬, 乔晓军, 赵春江, . 基于注意力机制与EfficientNet的轻量化水稻病害识别方法[J]. 中国农机化学报, 2022, 43(11): 172-181.
[13]	郭文娟, 冯全, 李相周. 基于农作物病害检测与识别的卷积神经网络模型研究进展[J]. 中国农机化学报, 2022, 43(10): 157-166.
[14]	石洪康, 肖文福, 黄亮, 胡丛武, 胡光荣, 张剑飞. 基于卷积神经网络的家蚕病害识别研究[J]. 中国农机化学报, 2022, 43(1): 150-.
[15]	杨英茹, 吴华瑞, 张燕, 朱华吉, 李瑜玲, 田国英, . 基于复杂环境的番茄叶部图像病虫害识别[J]. 中国农机化学报, 2021, 42(9): 177-186.