We investigate the application of a new category of low-level image descriptors termed interest points to remote sensed image analysis. In particular, we compare how scale and rot...
Web spam detection has become one of the top challenges for the Internet search industry. Instead of using some heuristic rules, we propose a feature re-extraction strategy to opt...
Content-based image retrieval (CBIR) systems target database images using feature similarities with respect to the query. Our CBIR demonstration utilises novel illumination invari...
Higher-level features based on linguistic or long-range information have attracted significant attention in automatic speaker recognition. This article briefly summarizes approac...
We present a probabilistic framework for correspondence and egomotion. First, we suggest computing probability distributions of correspondence. This has the advantage of being rob...