Image matching algorithm based on a local photometric and geometric data

One of the most famous and simplest matching methods based on photometric data is Winner Takes All. However, this approach presents the disadvantage of being non symmetrical, the solution to this problem consists on using a crossed matching, but all the key points don't find necessary their corresponding key points. In order to improve the matching results, a proposed solution consists on employing geometric constraints. In this paper, we propose two alternatives of matching approaches. The first one is based on photometric data, while the second one, uses both photometric and geometric data. Experimental results demonstrate that our proposed methods are efficient and give promising results in terms of repeatability and processing time.