Abstract
India is an agricultural country, and 70% of the population depends on agriculture, hence heavy crop losses due to plant diseases results in loss of several billion dollars annually. This paper mainly concentrates on detection of leaf diseases. In rural areas and in developed countries, the naked eye observation of agricultural experts to detect the plant diseases is cumbersome. It takes too much of cost and time. This paper aims to provide fast and cheap solution through automatic detection of leaf diseases and thus to improve the yield of the crops by detecting the plant diseases at earlier stage. Using image processing, we can able to identify the type of disease in plant leaf by analyzing the color and texture feature. In our system first, color transformation is done from RGB to HSV and followed by color feature extraction. In color feature analysis, the color distribution of pixels is represented by the mean and standard deviation of the image and local color information is represented by Binary bitmap. For texture feature extraction, first green pixels are masked as they are healthy region. This is followed by segmentation using K means clustering and identification of useful segments. Gray level co-occurrence matrix (GLCM) is obtained from the segmented image from which the texture features are extracted. Using SVM diseased plant is discriminated from the healthy plant and classified based on diseases. The performance of classification is measured using performance measures precision and recall.
Highlights
Plant disease can be defined as abnormal changes in the physiological processes brought about by any biotic or abiotic factor(s) which threatens the normal growth and reproduction of a plant
Automatic plant disease identification is our research topic to identify the diseases at the early stage
Texture features like Contrast, Energy, Local homogeneity, Cluster shade, and cluster prominence are computed for the H-component
Summary
Plant disease can be defined as abnormal changes in the physiological processes brought about by any biotic or abiotic factor(s) which threatens the normal growth and reproduction of a plant. As the naked eye observation technique requires continuous monitoring of the crops by experts, it’s expensive For this reason, automatic plant disease identification is our research topic to identify the diseases at the early stage. Patil et al have proposed techniques to classify different types of diseases in plant leaves and fruits in his review paper. Commonly used classifiers are neural networks and SVM. The paper, Detection, and classification of plant diseases, proposed by Niket Amoda et al.[4] used texture feature and neural networks for classification of diseases in tomato leaves. Arivazhagan.s et al [5] used texture analysis for detection of an unhealthy region of plant diseases and SVM the classifier. To identify and classify the grapefruit peel diseases Kim et al [6] have used low-level features such as color and texture.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Research in Computer Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
