Author : P.R. Rothe and R. V. Kshirsagar

Feature extraction is a significant constituent of a pattern recognition system. It carries out two assiginments: convertinging input parameter vector into a feature vector and/or reducing its dimensionality. A distinct feature extraction algorithm makes the classification process more effectual and effcient. The allocation and recognition of cotton leaf diseases are of the major importance as they have a cogent and momentous impact on quality and production of cotton. In this work we present a snake based approach for the segmentation of images of diseased cotton leaves.We extract Hu’s moments which can be used as shape descriptors for classification. A theory of two-dimensional moment invariants for planar geometric figures is also presented. Three diseases have been considered, namely Bacterial Blight, Myrothecium and Alternaria. The testing samples of the images are gathered from CICR Nagpur, cotton fields in Buldhana and Nagpur district.

Keywords: Cotton leaf diseases, Active contour model, Spatial moment, Central moments, Snake segmentation

Article published in International Journal of Current  Engineering  and Technology, Vol.4,No.2 (April- 2014)