Face identification systems relying on local descriptors are increasingly used because of their perceived robustness with respect to occlusions and to global geometrical deformati...
In this paper, we propose a probabilistic model for web image mining, which is based on concept-sensitive salient regions without human intervene. Our goal is to achieve a middle-...
Historical films usually have defects. We study the type of defects, and propose a series of solutions to detect defects before they are repaired by our inpainting algorithms. Thi...
This paper presents a new GPU-based tensor voting implementation which achieves significant performance improvement over the conventional CPU-based implementation. Although the t...
Trinetra aims for cost-effective, assistive technologies to provide blind people with a greater degree of independence in their daily activities. The overall objective is to impro...
Patrick E. Lanigan, Aaron M. Paulos, Andrew W. Wil...