Colour texture classification using wavelet transform from its gray scale

Texture is one of the significant ubiquitous image characteristics in an image. Texture classification approach is an important tool for many computer vision applications such as image retrievel, remote sensing, object recognition and many more. This paper presents a novel and simple texture classification system for colour textures by using patch based energy features from its gray scale image. The texture feature from the given image is captured by wavelet transformation. At first, color texture image is transformed into gray scale and multi resolution analysis of Discrete Wavelet Transformation (DWT) is applied to the transformed gray scale texture image. After that the proposed patch based energy features are extracted from the selected wavelet coefficients in each sub-band based on the edge intensities. K Nearest Neighbor (KNN) classifier is used for classification process. The performance of the system is evaluated by varying the decomposition level, number of selected wavelet coefficients and size of the patch used to extract the energy features. The proposed texture classification is carried out by using VisTex database. The satisfactory result is obtained from the proposed patch energy feature based texture classification system.