Image segmentation is a vital part of many applications because it makes possible for the information extraction and analysis of image contents.

Image processing is a comprehensively research topic with an elongated history. Segmenting

Since the development of internet and multimedia, image compression is emerging in all the fields like pattern recognition, image processing, system modeling, data mining, etc. Compression techniques have become the most concentrated area in the fields of computer. Image compression is a technique of efficiently coding digital image to reduce the number of bits required in representing an image. Many image compression techniques presently exist for the compression of different types of images. In this paper, Vector Quantization based compression technique is established with Modified Fuzzy Possibilistic C-Means (MFPCM) with repulsion. Repulsion technique aims to reduce the intra-cluster distances and also increases the inter-cluster distances. The residual codebook is used in this proposed approach which eliminates the distortion in the reconstructed image and thus enhancing the image quality. Moreover, the proposed technique replaces LBG algorithm with the modified fuzzy possiblistic c-means algorithm in the codebook generation. Experimental results on standard image Lena show that the proposed scheme can give a reconstructed image with higher PSNR value than the existing image compression techniques.

No abstract

Face recognition and retrieval is developed into a very active research area specializing on how to extract and recognize faces within images. The various methods has been proposed for face recognition and retrieval each methods has advantage and drawbacks. The complexity in process will affects performance of the existing system make insufficient. In this paper presented a Fiducial Point Feature based segmentation of face image in the generation of feature sets. The feature set is generated based on the fiducial points such as eye brow, eye, iris, mouth and nose are extracted and segment the image based on rectangular features. The feature is generated and matching is done by Euclidean distance is used to measures a distance between two images. The experimental result shows that Fiducial Point Feature method provides better recognition rate when compared with the existing methods such as PCA and PCA with DWT.