Area Based Image Matching Methods – A Survey

This paper aims to present a review of recent as well as classic area based image matching methods. Determination of three dimensional data from images is very important task in the machine vision field. Stereo vision has wide range of potential application areas including three dimensional reconstruction of a view. Matching algorithms play a key role in deciding correspondences between two image scenes. Mainly, the matching algorithms are distinguished as area based matching and feature based matching. Area based methods sometimes called correlation like methods or template matching, merge the feature detection step with the matching part. These methods deal with the images without attempting to detect salient objects. Windows of predefined size is used for the estimation of correspondence. The major goal of this paper is to provide comprehensive reference for the researchers involved in, area based image matching. Main contribution, advantages and drawbacks of the area based methods are mentioned in this paper. Keywords—Image matching, Correlation, Disparity, Fourier, Local algorithms