International Journal of Engineering Research and Development ISSN: 2278-067X, Volume 1, Issue 9 (June 2012), PP.55-59 www.ijerd.com 55 Fast Evolution of Curve Based On Chan-Vese Model for Specific Images Madhu Anand 1 , Vikram Singh 2 , Sumit Kaushik 3 1,2 CSA department, Ch.Devilal University Sirsa (INDIA) 3 GNI, Mullana (India) Abstract--In image processing, segmentation is an important intermediate step for object recognition. It is a fundamental task in image analysis responsible for partitioning an image into multiple sub-regions based on a desired feature. One such technique is through Curve Evolution and one of the applications of Geometric Curve Evolution is Active Contours. In the research work being reported in this paper an attempt has been made to enhance Chan-Vese [1] Algorithm faster by taking different planes (red, green and blue) of an image. The plane in which the contour evolves fastest gets automatically selected and rest of the algorithm will work on that particular plane. Experimental results are presented on various domains like biomedical images, artificial images and painted images. Also, the contour evolves differently in different planes. Key Terms- active contour, objects, object recognition, segmentation, standard deviation I. INTRODUCTION Segmentation is an intermediate step in all high level object-recognition tasks. For example, if we want to locate the face of a particular person in an image of a crowd, we should first determine that which parts of the image correspond to human faces. Active Contours have been widely used as attractive image segmentation methods because they always produce sub-regions with continuous boundaries. For instance, starting with a curve around the object to be detected, the curve moves toward its interior normal and has to stop on the boundary of the object. An object in image processing is an identifiable portion of an image that can be interpreted as single unit. The active contour model is more and more used in image segmentation because it relies on solid mathematical properties and its numerical implementation uses the level set method to track evolving contours. The motion of the curve is driven by the image itself. The driving force is obtained by defining a potential in the image that shall be small near objects contours. If β is a grey level image, the external potential is defined at each point of the image and is of the type g(x) = 1 (1+ǀDGσ*βǀ2) where G is a gaussian with standard deviation s. The term appearing in the denominator is the gradient of a regularized version of the image ( * denotes convolution.) Active contours can be classified as parametric active contours and geometric active contours according to their representation and implementation. Geometric active contours were in use now a days, which provide solution to tackle the problem of topological changes required in curve evolution. In [5] a precise relationship between the geometric and parametric active contours has been developed which includes spatially-varying coefficients, both tension and rigidity, and non-conservative external forces. Geometric deformable models implemented using level set methods have advantages over parametric models due to their intrinsic behavior, parameterization independence, and ease of implementation. Active contour models are also used for 2D and 3D biomedical images formulated using the level set method [6].These models can also be generalized to segmentation of images with more than two segments. Snakes are also active contour models [7]-they lock onto nearby edges, localizing them accurately. Snakes were used extensively in image processing applications, particularly to locate object boundaries. An improved region-based active contour/surface model for 2D/3D brain MR image segmentation is introduced in [8].The model combines the advantages of both local and global intensity information, which enable the model to cope with intensity in homogeneity.