Combining gray level and gradient magnitude for scene matching

A correlation algorithm for scene matching by using two intensity features, i.e., gray level and gradient magnitude, is proposed. The correlation surface produced by the algorithm is the simple summation of the two ones obtained by using gray level and gradient magnitude respectively with zero mean normalized cross correlation similarity measure. We show that theoretically the proposed method will give better matching performance compared to the correlation algorithm by either gray level or gradient magnitude only under some conditions. Experimental results with real images demonstrate that the new algorithm can even report better results than classical algorithms and some newly presented ones.