Robust image matching algorithm

Image matching is an important task. There are many available methods for occluded image matching, e.g., Hausdorff distance and wavelet transform based matching. In this paper we propose new simple image-matching algorithm, robust image matching algorithm (RIMA), an extension to distance transform (chamfer) matching. Distance transform and conventional chamfer matching algorithm are explained. Different matching measures for RIMA are presented. Examples to demonstrate the algorithm and necessary results are also included. Proposed RIMA is time efficient, robust, rotation, scale and perspective invariant method.