We are currently working on this web.
IRAM Lab aims to propose new metaheuristic-based approaches to solve the image registration problem.
Image registration is a fundamental task in computer vision used to finding a correspondence (or transformation) among two or more pictures taken under different conditions: at different times, using different sensors, from different viewpoints, or a combination of them. Over the years, registration has been applied to a broad range of situations from remote sensing to medical images or artificial vision, and different techniques have been independently studied resulting in a large body of research.
Recently, a new family of search and optimization algorithms has arisen based on extending basic heuristic methods by including them into an iterative framework augmenting their exploration capabilities. These group of advanced approximate algorithms have received the name of metaheuristics.
In the last few years, there is an increasing concern on applying metaheuristics to the image registration problem. Especially, there is increasing interest on applying Evolutionary Computation (EC) fundamentals to the image registration. Unfortunately, we can find a lack of accuracy when facing this problem and different contributions fall into problem simplifications or, even worse, apply EC concepts not in the more suitable way.