An Efficient Image Matching Algorithm Muhammad Saleem; Adil Masood Siddiqi; Imran Touqir

摘要

The problem of matching two images has been an active topic of research in computer vision, pattern recognition, robotics and image analysis. Matching Algorithms based on low level features are computationally expensive, because the edge image of template or its distance transforms are translated and superimposed on all the pixels of reference image. Matching is achieved by calculating the minimum distance out of all the translations. The problem is further aggravated if reference image is of much greater dimensions as compared to template image. Since the reference image consists of objects and background, calculating the minimum distance for all the pixel locations becomes time consuming. In this paper a method to decrease the computation time of existing algorithms is presented, to make existing schemes suitable for real time matching.