OCR systems for Indian scripts are now available commercially at affordable prices and can recognize multiple fonts. On the other hand, not much research work towards recognition of handwritten characters of Indian scripts has been done. Unfortunately, the technology of printed OCR cannot be extended to recognition of handwritten characters due to enormous variability in people's handwriting styles.


Devanagari is the first-most popular language and script of India while Bangla is the second-most popular language and script in the Indian subcontinent and the fifth-most popular language in the world. There are several other scripts such as Tamil, Telegu, Kanada, Malayalam and a few others, which are used by significant sections of Indian population.


Most of the available works on handwriting recognition of Indian scripts are based on small databases collected in laboratory environments. Recently, we developed a few large databases of handwritten characters of major Indic scripts. These database are the following.


1.      Online handwritten database

(a)   Bangla numerals

(b)   Bangla basic characters

2.      Offline handwritten database

(a)   Numerals

(i)     Devanagari

(ii)   Bangla

(iii) Oriya

(b)   Basic characters

(i)     Bangla

(ii)   Devanagari

(c)    Bangla Vowel Modifiers

(d)   Bangla Compound characters

Application form for obtaining "ISI Handwritten Character Databases"


Back to Ujjwal's main page