: We present a symbol recognition method without segmentation of the document. Our approach uses Zernike moments for the coding and a multilayered Perceptron for the classifier. Re...
Many approaches to Information Extraction (IE) have been proposed in literature capable of finding and extract specific facts in relatively unstructured documents. Their applicatio...
With an aim to high-level understanding of the mathematical contents in a document image the requirement of math-zone extraction and recognition technique is obvious. In this pape...
S. P. Chowdhury, S. Mandal, Amit Kumar Das, Bhabat...
A new approach for separating mathematics from usual text is presented. Contrary to the existing methods, it is more oriented toward the segmentation than the recognition, isolati...
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...