To search a pattern or a template in a reference image is an essential step in a number of image processing applications. We often focus on searching some parts of the original large image through out the whole reference one for the accurate position and orientation. In this paper, a multiscale matching approach based on the mutual information model is proposed. And we also discuss the possible means to decrease the amount of computation in the search technique by limiting the entire set of possible locations in a small subset ones. The performance and results of the algorithm is demonstrated. The explicit application is the automatic terrain navigation. Other applications involve image database query, partial-content based indexing, and image positioning etc.
展开▼