Author : Ritika Nain and Naresh Kumar

The primary contribution of this research is the development of computational frameworks that tackle in a general and principled way the problems arising in the construction of an image registration system. A novel algorithm for image features matching is used in terms of evolutionary algorithms. We have efficiently used the gravitational search algorithm (GSA) to match image features by tuning the rotational angle of image. The complete work is divided into three modules: edge detection, features extraction and features matching. After studying previous work on this, we used the effective phase congruency method for the edge detection to avoid non uniform illumination problem occurred in detection of edges. The requirement of features extraction is that matching points which don’t change even after change in angle of rotation of image. So we used scale invariant features transform (SIFT) method to extract features and finally we purposed the tuned matching algorithm which can work for almost every type of image. Our features matching using GSA algorithm tune the rotational angle of test image and set it to an optimum angle so that it can best match with the reference image.

Keywords: Gravitational search algorithm etc.

Article published in International Journal of Current Engineering and Technology, Vol.6, No.2 (April-2016)