Analysis of Leaf Diseases using Learning Image Superresolution

Abstract

Superresolution is a process of extracting higher details. The main objective of this paper is the study of patch based method for super-resolving low resolution of a leaf diseased image. The domain specific prior is incorporated into superresolution by the means of learning patch based estimation of missing high frequency details from infected leaf image. Images are decomposed into fixed size patches in order to deal with time and space complexity. The problem is modeled by Markov Random Field which enforces resulting images to be spatially consistent. The spatial interactions are coupled with a similarity constraint which should be established between high-resolution training image patches and low resolution observations of leaf diseased images. Through this proposed work, fine edges of SR images are preserved without applying complex mathematical algorithms based on wavelet, fast curvelet, etc. Also gives the better visual SR image as that of complex multi frame SR algorithms like reconstruction and registration. This concept is most useful for agricultural expert for helping our farmers. The experimental result shows the best visible SR result of an infected leaf along with MSE and PSNR.