Robust extraction of text from scene images is essential for successful scene text recognition. Scene images usually have non-uniform illumination, complex background, and existen...
We propose an unsupervised approach to learn associations between continuous-valued attributes from different modalities. These associations are used to construct a multi-modal t...
With an aim to extract the structural information from the table of contents (TOC) to help develop digital document library the requirement of identifying/segmenting the TOC page ...
S. Mandal, S. P. Chowdhury, Amit Kumar Das, Bhabat...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
Many man-made and natural structures consist of similar elements arranged in regular patterns. In this paper we present an unsupervised approach for discovering and reasoning on re...