For a list of all papers click here

Saturday, 31 March 2012

Sampling Strategies in Computer Vision

This work with Mosalam Ebrahimi looks at ways to sample images and data for making computer vision algorithms more efficient. The question is not whether things can be faster but what data should an algorithm work with. The results can be algorithms that are faster and have very close performance to an algorithm that uses the entire image. Sampling can be extended to other parts of a visual pipeline and work is under way.