U
Umapada Pal
Researcher at Indian Statistical Institute
Publications - 478
Citations - 11707
Umapada Pal is an academic researcher from Indian Statistical Institute. The author has contributed to research in topics: Feature extraction & Handwriting recognition. The author has an hindex of 47, co-authored 478 publications receiving 9925 citations. Previous affiliations of Umapada Pal include University of Mysore.
Papers
More filters
Proceedings ArticleDOI
A scale and rotation invariant scheme for multi-oriented Character Recognition
TL;DR: This paper presents a multi-scale and multi-oriented character recognition scheme using foreground as well as background information and it has been seen that the proposed methodology outperforms a recent competing method.
Journal ArticleDOI
Piece-wise linearity based method for text frame classification in video
TL;DR: A new piece-wise linearity based method is proposed for text frame classification that is computationally less expensive and outperformed existing methods in terms of classification rate and processing time.
Journal ArticleDOI
Semiautomatic Ground Truth Generation for Text Detection and Recognition in Video Images
Trung Quy Phan,Palaiahnakote Shivakumara,Souvik Bhowmick,Shimiao Li,Chew Lim Tan,Umapada Pal +5 more
TL;DR: A semiautomatic system for ground truth generation for video text detection and recognition, which includes English and Chinese text of different orientation, and has a facility to allow the user to manually correct the ground truth if the automatic method produces incorrect results.
Proceedings ArticleDOI
Adaptive Multi-Gradient Kernels for Handwritting Based Gender Identification
B.J. Navya,Palaiahnakote Shivakumara,G.C Shwetha,Sangheeta Roy,Devanur S. Guru,Umapada Pal,Tong Lu +6 more
TL;DR: A new adaptive multi-gradient of Sobel kernels for extracting Adaptive Multi-Gradient Features (AMGF), which finds dominant pixels based on directional symmetry of text pixels given by AMGF and outperforms the existing methods.
Proceedings ArticleDOI
Multiple Training - One Test Methodology for Handwritten Word-Script Identification
TL;DR: A Multiple Training - One Test technique to alleviate the problem of script identification at word level on documents written in multiple scripts and Accuracy improvements has been obtained with this promising technique, especially for the shorten words.