Publications

Abstract : Wireless multimedia sensor networks (WMSNs) attracts significant attention in the field of agriculture where disease detection plays an important role. To improve the cultivation yield of plants it is necessary to detect the onset of diseases in plants and provide advice to farmers who will act based on the received suggestion. Due to the limitations of WMSN, it is necessary to design a simple system which can provide higher accuracy with less complexity. In this paper a novel disease detection system (DDS) is proposed to detect and classify the diseases in leaves. Statistical based thresholding strategy is proposed for segmentation which is less complex compared to k-means clustering method. The features extracted from the segmented image will be transmitted through sensor nodes to the monitoring site where the analysis and classification is done using Support Vector Machine classifier. The performance of the proposed DDS has been evaluated in terms of accuracy and is compared with the existing k-means clustering technique. The results show that the proposed method provides an overall accuracy of around 98%. The transmission energy is also analyzed in real time using TelosB nodes.