Citrus Leaf Disease Detection using Joint Scale Local Binary Pattern
Plant diseases are known from early times of cultivation and is also considered as one of the major factors affecting crops growth and quantity. Such losses from plant diseases can have a substantial economic impact, causing a reduction in income of farmers and higher prices for consumers. Today’s agriculture demands regular use of high-tech technologies such as robots, moisture sensors, aerial surveillance and images processing. These technological shifts allow farmer to be more profitable and more environmentally friendly. This paper investigates and present Joint Scale Local Binary Pattern (JS-LBP) algorithm for detection of plant leaf disease based on image segmentation and texture analysis. The proposed method consists of two main phases, identification of disease lesion spot on citrus leaves and its classification. Leave images are pre-processed using top-hat filtering and two median filters, later these images are fed into the JS-LBP descriptor for feature extraction. Experiment shows that proposed algorithm attains 98.6% accuracy rate. Confusion matrix and ROC curve for different citrus diseases are also presented.
Copyright (c) 2020 University of Sindh, Jamshoro
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
University of Sindh Journal of Information and Communication Technology (USJICT) follows an Open Access Policy under Attribution-NonCommercial CC-BY-NC license. Researchers can copy and redistribute the material in any medium or format, for any purpose. Authors can self-archive publisher's version of the accepted article in digital repositories and archives.
Upon acceptance, the author must transfer the copyright of this manuscript to the Journal for publication on paper, on data storage media and online with distribution rights to USJICT, University of sindh, Jamshoro, Pakistan. Kindly download the copyright for below and attach as a supplimentry file during article submission