Subhadip Basu

TL;DR: A methodology where local regions of varying heights and widths are created dynamically and genetic algorithm (GA) is applied on these local regions to sample the optimal set of local regions from where an optimal feature set can be extracted that has the best discriminating features.

TL;DR: A new combination of PCA/MPCA and QTLR features for OCR of handwritten numerals is introduced and it has been observed that MPCA+QTLR feature combination outperforms PCA+QTB feature combination and most other conventional features available in the literature.

TL;DR: This paper has described the preparation of a benchmark database for research on off-line Optical Character Recognition (OCR) of document images of handwritten Bangla text and Bangle text mixed with English words, which is the first handwritten database in this area available as an open source document.

TL;DR: A novel text line extraction technique is presented for multi-skewed document images of handwritten English or Bengali text that assumes that hypothetical water flows, from both left and right sides of the image frame, face obstruction from characters of text lines.

TL;DR: A novel hierarchical approach is presented here for optical character recognition (OCR) of handwritten Bangla words that segments a word image on Matra hierarchy, then recognizes the individual word segments and finally identifies the constituent characters of the word image through intelligent combination of recognition decisions of the associated word segments.