Texture image classification and its Applications using multi resolution Combined statistical and spatial Frequency method

Abstract

Texture Analysis has been an extremely active and fruitful area of newlineresearch over the past twenty years Today texture analysis plays an important newlinerole in many tasks ranging from remote sensing to medical image analysis newlineThe main difficulty of texture analysis method was the lack of tools to newlineanalyze different characteristics of texture images Texture analysis is broadly newlineclassified as texture classification texture segmentation texture synthesis and newlineshape recovery from textures newlineAmong the above texture classification is a trendy and catchy newlinetechnology in the field of texture analysis Texture classification is important newlinein many applications like image database retrieval industrial agricultural and newlinebio medical applications Texture classification is based on three different newlineapproaches they are statistical spectral and structural newlineStatistical approaches are based on statistical properties in gray newlinelevel of the image Statistical approaches include first order statistical newlineproperties like spatial texture energy texture mean texture variance second newlineorder statistical properties like autocorrelation function Gray Level newlineCo occurrence Matrix GLCM Markov Random Field Matrix MRFM newline