期刊名称：Advanced Computing : an International Journal
印刷版ISSN：2229-726X
电子版ISSN：2229-6727
出版年度：2016
卷号：7
期号：1/2
页码：39
DOI：10.5121/acij.2016.7205
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Color, texture, shape and luminance are the prominent features for image segmentation. Texture is anorganized group of spatial repetitive arrangements in an image and it is a vital attribute in many imageprocessing and computer vision applications. The objective of this work is to segment the texture subimages from the given arbitrary image. The main contribution of this work is to introduce “NEW” texturefeature descriptor to the image segmentation field. The NEW texture descriptor labels the neighborhoodpixels of a pixel in an image as N,W,NW,NE,WW,NN and NNE(N-North, W-West).To find the predictionvalue, the gradient of the intensity functions are calculated. Eight component binary vectors are formedand compared to prediction value. Finally end up with 256 possible vectors. Fuzzy c-means clustering isused to segment the similar regions in textural image Extensive experimentation shows that the proposedmethodology works better for segmenting the texture images, and also segmentation performance areevaluated.
