期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：11
DOI：10.15680/IJIRCCE.2015.0311131
出版社：S&S Publications
摘要：The large number of people depends on cotton crop. The recognition of cotton leaf disease are of themajor important as they have a cogent and momentous impact on quality and production of cotton. Cotton diseaseidentification is an art and science. The start with collecting the images. We will consider two diseases they are Foliar,and Alternaria of cotton leaves. We have extracted the features and compare those features with the features that areextracted from the input test image they can like grayscaling, thresholding, cropping for detecting the boundary ofimage. Colour feature like HSV features are extracted from the output of segmentation and (ANN) artificial neuralnetwork is trained by choosing the feature value that could distinguish the healthy and disease sample. Experimentalresult showed that classification performance by ANN taking feature set is better with an accuracy of 80%. The presentwork proposes a methodology for detecting cotton leaf disease early, using image processing techniques and artificialneural network (ANN).
