Kuan noise filter with Hough transformation based reweighted linear program boost classification for plant leaf disease detection

In agriculture, plant leaf disease detection is significant concern to attain high crop yield and production. The product quality and productivity are affected, when proper care is not taken, it causes severe effects on plants. Several standard techniques have been developed for disease classification. The major issue facing these techniques is the automatic identification of plant diseases with minimal processing time. In order to improve the disease detection accuracy (DDA) with minimum time, Kuan filtered Hough transformation based reweighted linear program boost classification (KFHT-RLPBC) technique is introduced. KFHT-RLPBC technique includes three processes such as pre-processing, feature extraction and classification. A number of leaf images are gathered from plant dataset. In the pre-processing, the noises in the input leaf images are removed using Kuan filter to improve the image quality for achieving the higher disease detection accuracy. The Hough transform is utilized for extracting shape, texture and color features. KFHT-RLPBC technique reduces the time complexity (TC) in disease identification through the feature extraction process. Finally, the classification is done by applying the reweighted linear program to boost classification (RLPBC) to identify the disease at an earlier stage by constructing the number of weak learners. The boosting classifier combines the weak learner results and makes a strong one for achieving higher disease detection accuracy with minimum error. With plant village dataset, experimental evaluation is performed using certain parameters namely peak signal to noise ratio, disease detection accuracy and time complexity. Experimental results confirm that KFHT-RLPBC technique enhances disease detection accuracy and peak signal to noise ratio and reduces time complexity than the existing works.