While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle pe...
We present an irregular image pyramid which is derived from multi-scale analysis of segmented watershed regions. Our framework is based on the development of regions in the Gaussia...
VIMS Lab is situated in Department of Computer & Information Sc, University of Delaware, Newark, DE. USA.
At VIMS we work on various problems related to image/video processing...
This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...
We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to ...