Classification of Pomegranate Diseases Based on Back Propagation Neural Network

A B S T R A C T This paper presents a study of Back Propagation Neural Network (BPNN) classifier for detection of plant diseases based on visual symptoms occurring on leaves. Two diseases of pomegranate plant namely Bacterial Blight (BB) and Wilt Complex (WC) are considered as study objects. Images of healthy and unhealthy leaf samples are captured by digital camera, enhanced and segmented to detect infected portions. Color and texture features are extracted and passed through BPNN classifier which correctly classifies the disease being occurred, thereby helping farmers in effective decision making. Analysis results show that the proposed classifier yields an accuracy of 97.30%.

[1]  Malik Braik,et al.  Detection and Classification of Leaf Diseases using K-means-based Segmentation and Neural-networks-based Classification , 2011 .

[2]  A. Srikaew,et al.  Grape leaf disease detection from color imagery using hybrid intelligent system , 2008, 2008 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[3]  J. Sil,et al.  Rice disease identification using pattern recognition techniques , 2008, 2008 11th International Conference on Computer and Information Technology.

[4]  Darrell D. E. Long,et al.  Exploring the Bounds of Web Latency Reduction from Caching and Prefetching , 1997, USENIX Symposium on Internet Technologies and Systems.

[5]  Libo Liu,et al.  Extraction of the Rice Leaf Disease Image Based on BP Neural Network , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[6]  Daniel E. Guyer,et al.  Apple Grading Using Fuzzy Logic , 2003 .

[7]  Jeremy S. Smith,et al.  An image-processing based algorithm to automatically identify plant disease visual symptoms. , 2009 .