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：2017
卷号：5
期号：8
页码：13994
DOI：10.15680/IJIRCCE.2017.0508022
出版社：S&S Publications
摘要：Betelleaves contain many remedial and medicinal health benefits. During cultivation, betel vine ismainly affected by various diseases. The key feature of this work is to identify the diseases in earlier stage using imageprocessing techniques. Different stages of healthy and diseased betel leaf digital images have been transformed intol*a*b model using CIELAB color space. Watershed transformation algorithm is used for segmentation. Histograms ofOriented Gradients (HOG) technique has been used to extract the features. Then diseases are identified by usingmulticlass SVM classifier. Finally based on the evaluation metrics sensitivity and specificity, the proposed methoddepicted an improved accuracy of 95.85% compared to the existing one which is of 82.35% accuracy.
关键词：CIELAB Color Space Model; Watershed Segmentation; Histogram of Oriented Gradients; Multiclass;Support Vector Machine.
