Texture Segmentation Based on Gabor Filters and Neutrosophic Graph Cut

Image segmentation is the first step of image processing and image analysis. Texture segmentation is a challenging task in image segmentation applications. Neutrosophy has a natural ability to handle the indeterminate information. In this work, we investigate the texture image segmentation based on Gabor filters (GFs) and neutrosophic graph cut (NGC). We proposed an image segmentation approach, which applies GFs to gray-level images to extract image features matrix, and it segments them into regions. First, color images are transformed to gray level images as input images. Then, input parameters of GFs are adjusted, and GFs are performed on the input images to extract features. The NGC is employed for classification of input images. Finally, experiments are conducted on various natural images to evaluate the approach. Experimental results show that the proposed approach achieves desired performance of texture segmentation. However, it cannot segment the texturefree images as well as texture images. In future works, we will try to segment both texture images and texture-free images at the same time. Keywords— Image segmentation, texture segmentation, Gabor filters, Neutrosophic Graph Cut.