Fast Template Matching Based on Local Entropy Difference

A very efficient algorithm was proposed for fast template matching. The coarse-to-fine strategy was adopted in this algorithm. At coarse searching stage, local entropy difference was employed for template and sub-window of characterizing. Moreover, integral image and square integral image of the input image were utilized to speed up the local entropy difference calculating. After obtaining the local entropy differences between every position from the input image, the candidates table was built by threshold determining. At the fine searching stage, a new matching criterion, called as compound correlation (CC), was introduced for the best similar position within candidates table. The efficiency of the proposed algorithm was compared to FFT-based normalized cross correlation algorithm (NCCA) and sequential similarity detection algorithm (SSDA) which was based on resolution-reducing. The experimental results have shown that the proposed algorithm consumed less time in template matching than FFT-Based NCC and SSDA. Moreover, it performed better in robustness than SSDA.