Tomato leaves diseases detection approach based on Support Vector Machines

The study described in this paper consists of a method that applies gabor wavelet transform technique to extract relevant features related to image of tomato leaf in conjunction with using Support Vector Machines (SVMs) with alternate kernel functions in order to detect and identify type of disease that infects tomato plant. Initially, we collected real samples of diseased tomato leaves, next we isolated each leaf in single image, wavelet based feature technique has been employed to identify an optimal feature subset. Finally, a support vector machine classier with different kernel functions including Cauchy kernel, Invmult Kernel and Laplacian Kernel was employed to evaluate the ability of this approach to detect and identify where tomato leaf infected with Powdery mildew or early blight. To evaluate the performance of presented approach, we present tests on dataset consisted of 100 images for each type of tomato diseases. Extensive experimental results demonstrate that the proposed approach provides excellent annotation with accuracy 99.5 %. Efficient result obtained from the proposed approach can lead to tighter connection between agriculture specialists and computer system, yielding more effective and reliable results.