We introduce spatial PACT (Principal component Analysis of Census Transform histograms), a new representation for recognizing instances and categories of places or scenes. Both pl...
W e introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavele...
Abstract. We exploit the recurrence of structures at different locations, orientations and scales in an image to perform denoising. While previous methods based on "nonlocal f...
Yifei Lou, Paolo Favaro, Stefano Soatto, Andrea L....
In this paper we present a system to locate, extract and recognize Telugu text. The circular nature of Telugu script is exploited for segmenting text regions using the Hough Trans...
Atul Negi, K. Nikhil Shanker, Chandra Kanth Chered...
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...