Abstract: Texture segmentation is the process of partitioning an image into regions with different textures containing similar group of pixels. The color and texture information collectively has strong link with the human perception. So many applications need to combine color and texture features analyse the image content accurately. This study presents an unsupervised color texture image segmentation method which is based on the feature extraction and fuzzy clustering. The proposed method includes color texture segmentation using Haralick features extracted from Integrated Color and Intensity Co-occurrence Matrix (ICICM). Then, α-cut implemented interval type-2 fuzzy c-mean clustering algorithm is utilized to cluster the obtained feature vectors into several classes corresponding to different regions of the textured image. Experimental result shows that the proposed hybrid approach could obtain better cluster quality and segmentation results compared to state of art image segmentation algorithms.
P. Murugeswari and D. Manimegalai, 2012. Adaptive Color Texture Image Segmentation Using α-Cut Implemented Interval Type-2 Fuzzy C-Means. Research Journal of Applied Sciences, 7: 258-265.