A novel image template matching based on particle filtering optimization

Image template matching is a basic and crucial process for image processing. In this paper, we propose a new particle filtering optimization approach to image template matching. The proposed method combines the sum of squared differences (SSD) or zero mean sum of absolute differences (ZSAD) with normalized cross correlation (NCC) by Gaussians. As to the computation cost, the fusion-based approach is rather slow. The particle filter and chaos are utilized to calculate a portion of the searching field. In this way, the computational cost can be reduced. In order to comparatively assess the effectiveness of the proposed approach with respect to competing state-of-art techniques for different matching tasks, series of experiments on a variety of images have been conducted. The experimental results show the superior performance of the proposed method over the conventional full-search method with respect to variation such as illumination changes, noisy environments.