RESEARCH ON THE SEGMENTATION OF RICE LEAF BLAST SPOTS BASED ON COLOR SPACE AND PSO-IMPROVED BP NEURAL NETWORK

被引：0

作者：

Wang H. ^{[1
]}

Xiao M. ^{[2
]}

机构：

[1] College of Digital Equipment, Jiangsu Vocational and Technical College of Electronics and Information, Huaian

[2] College of Engineering, Nanjing Agricultural University, Nanjing

来源：

International Journal of Mechatronics and Applied Mechanics | 2023年 / 2023卷 / 13期

关键词：

BP neural network; Color space feature; Lesion segmentation; PSO; Rice leaf blast;

D O I：

10.17683/ijomam/issue13.6

中图分类号：

学科分类号：

摘要：

Rice blast is one of the four major diseases of rice. Once that happens, the yield will be greatly reduced. Image segmentation is the key link of rice blast identification, and its real-time and accuracy have a great impact on the accuracy of rice blast identification. Affected by factors such as crop texture distribution, complex background and blurred disease spots, there is currently no efficient and high-accuracy image segmentation method for rice leaf blast. In this study, by analyzing the colour characteristics of rice blast lesions, the 2R-G+B colour space component is innovatively used as the input feature of the neural network, which has excellent results, and Particle Swarm Optimization (PSO) is used to optimize the back propagation (BP) neural network. Finally, the model is trained and tested. The results show that the method using PSO to improve BP can achieve an average image segmentation similarity of 93.97%, which has obvious advantages compared with other existing image segmentation models. The method has a fast iteration speed, and at the same time, it effectively avoids the neural network falling into a local minimum, and provides an effective new method for the existing rice leaf blast image segmentation technology. © 2023, Cefin Publishing House. All rights reserved.

引用

页码：48 / 57

页数：9

共 23 条

[1] Shi F., Zhao K., Meng Q., Ma L., Research on Image Segmentation of Rice Blast Based on Support Vector Machine, Journal of Northeast Agricultural University, 44, pp. 128-135, (2013)
[2] Ren Y., Zhang G., Ma J., Wang Y., Zhang L., Deng L., Analysis on the Harm and Control of Rice Blast, Shanxi Agricultural Economics, 13, (2017)
[3] Hamuda E., Glavin M., Jones E., A Survey of Image Processing Techniques for Plant Extraction and Segmentation in the Field, Computers and Electronics in Agriculture, 125, pp. 184-199, (2016)
[4] Huang P., Zheng Q., Liang C., Overview of Image Segmentation Methods, Journal of Wuhan University (Science Edition), 66, pp. 519-531, (2020)
[5] Wang C., Lu C., Chen W., Li H., He J., Wang Q., Image Segmentation of Corn Stubble Row Based on Genetic Algorithm and Threshold Filtering, Chinese Journal of Agricultural Engineering, 35, 16, pp. 198-205, (2019)
[6] Chen J. D., Chen J. X., Zhang D. F., Sun Y. D., Nanehkaran Y. A., Using Deep Transfer Learning for Image-Based Plant Disease Identification, Computers and Electronics in Agriculture, 173, (2020)
[7] Yogeshwari M., Thailambal G., Automatic Feature Extraction and Detection of Plant Leaf Disease Using Glcm Features and Convolutional Neural Networks, Materials Today: Proceedings, (2021)
[8] Zhang W., Zhu M., Zhang N., Dong L., A Method of Plant Image Segmentation under the Color Cast Light Based on Convolutional Neural Network, computer application, 39, 12, pp. 3665-3672, (2019)
[9] Ashwinkumar S., Rajagopal S., Manimaran V., Jegajothi B., Automated Plant Leaf Disease Detection and Classification Using Optimal Mobilenet Based Convolutional Neural Networks, Materials Today: Proceedings, 51, pp. 480-487, (2022)
[10] Zhang M., Wang S., Guo X., Yan Z., Image Segmentation of Potato Disease Based on Hybrid Leapfrog Algorithm Optimization of Pcnn, Journal of Plant Protection, 45, pp. 322-331, (2018)

← 1 2 3 →