Effective Object Localization in Images by Calculating Ratio and Distance Between Pixels

Abstract

In this paper, two novel similarity functions which consider the spatial and brightness relations between pixels for object localization in images are presented. We explore different advantages of our functions and compare them to others that use only spatial connection between pixels. It is shown, that one of them is robust to linear change in pixel brightness levels of the compared images. Comparison of computational cost and localization accuracy of shifted object for our similarity functions with others is given in the paper. The presented experimental results confirm the effectiveness of the proposed approach for object localization.