Texture classification became one of the problems which has been paid muchattention on by image processing scientists since late 80s. Consequently, sincenow many different methods have been proposed to solve this problem. In most ofthese methods the researchers attempted to describe and discriminate texturesbased on linear and non-linear patterns. The linear and non-linear patterns onany window are based on formation of Grain Components in a particular order.Grain component is a primitive unit of morphology that most meaningfulinformation often appears in the form of occurrence of that. The approach whichis proposed in this paper could analyze the texture based on its graincomponents and then by making grain components histogram and extractingstatistical features from that would classify the textures. Finally, toincrease the accuracy of classification, proposed approach is expanded to colorimages to utilize the ability of approach in analyzing each RGB channels,individually. Although, this approach is a general one and it could be used indifferent applications, the method has been tested on the stone texture and theresults can prove the quality of approach.
展开▼