当前位置: X-MOL 学术J. Sci. Ind. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An Integrated Image Processing Approach for Diagnosis of Groundnut Plant Leaf Disease using ANN and GLCM
Journal of Scientific & Industrial Research ( IF 0.6 ) Pub Date : 2020-07-09
K Gowrishankar, S Lakshmi Prabha

The plants are highly significiant for human life and animal life. Plants also suffer from illness (i.e., diseases) like humans and animals. Groundnut plant is more prone to diseases in the agriculture sector. Cercospora is the most common leaf disease in the groundnut. Entire plant gets infected by the diseases which include stem, root, flower and leaves. For controlling and managing the diseases human involvement is necessary as it is time consuming for classification and recognition of groundnut leaf diseases. The process is longer and costlier hence an automatic image processing method is adopted. In this paper, the images of groundnut leaves are collected and preprocessed by median filter. The preprocessed images are segmented by multi threshold based color segmentation. These segmented images are fed to feature extraction by Gray Level Co-ocurrance Matrix (GLCM) and feature selection by rough set approach and the leaf diseases are classified by ANN and SVM classifier. Finally the performance measures are made by comparing the accuracy and sensitivity of ANN and SVM classifiers to prove the effectiveness of ANN.

中文翻译:

基于ANN和GLCM的花生叶片病害综合图像处理方法。

这些植物对人类和动物生命具有重要意义。植物还遭受人类和动物等疾病(即疾病)的折磨。花生植物在农业部门中更容易患病。Cercospora是花生中最常见的叶病。整个植物都受到茎,根,花和叶等疾病的感染。为了控制和管理这些疾病,需要人类参与,因为对花生叶病进行分类和识别非常耗时。该过程较长且昂贵,因此采用自动图像处理方法。本文通过中值滤波器对花生叶片图像进行采集和预处理。预处理的图像通过基于多阈值的颜色分割进行分割。这些分割后的图像通过灰度共生矩阵(GLCM)进行特征提取,并通过粗糙集方法进行特征选择,叶病通过ANN和SVM分类器进行分类。最后,通过比较神经网络分类器和支持向量机分类器的准确性和敏感性来进行性能度量,以证明神经网络的有效性。
更新日期:2020-07-28
down
wechat
bug