Detection and Classification of Plant Diseases
The proposed approach can successfully detect and classify the examined diseases with a precision between 83% and 94%, and able to achieve 20% speedup over the approach proposed in (1).
Abstract
We proposed software solution for automatic classification and detection of plant leaf diseases. Which is an improvement to the solution proposed in (1) as it will be able to provide quick and more accurate solution. The process consists of four main phases as mentioned in (1). The following extra two steps are required to add successively after the segmentation phase. In the first step we find the mostly green colored pixels. And in second step, these green pixels are masked based on their specific threshold values which will computed using Otsu's method, then those mostly green pixels are masked. The other additional step is that the pixels with zeroes R.G.B. values and the pixels on the boundaries of the infected cluster are completely removed. The experimental results indicate that the proposed technique is a fast and accurate technique for the detection of plant leaves diseases. The proposed approach can successfully detect and classify the examined diseases with a precision between 83% and 94%, and able to achieve 20% speedup over the approach proposed in (1).