Venu Govindaraju

TL;DR: The several paradigms that have been developed to solve the problem of recognizing handwritten words are described and how each is suitable for a particular category of applications is shown.

TL;DR: This work presents methods that make robust the previous Markov random field (MRF)-based approach for pointer recognition and ROI extraction, including use of Active Shape Models (ASM) to overcome problems in recognizing distorted pointer shapes and a region segmentation method forROI extraction.

TL;DR: This chapter describes the use of a script specific Keyword Spotting for Sanskrit documents that makes use of domain knowledge of the script and addresses the needs of a digital library to provide access to a collection of documents from multiple scripts.

TL;DR: This work calculates an orientation coherence map and determines minimum coherence regions as high-curvature areas and applies smoothing operation to local ridge shape structures, which efficiently joins broken ridges without destroying essential singularities and enforces continuity of directional fields even in creases.