The Oriya script developed from the Kalinga script, one of the many descendants of the Brahmi script of ancient India. Our database of isolated handwritten Oriya numerals consists of 5970 samples from 356 persons. This database was formed from 105 mail pieces, 166 job application forms and for the rest we used the third type of form described above. The whole set of available data have been split into a training set consisting of 4970 samples and a test set consisting of 1000 samples.
Ref:- U. Bhattacharya and B. B. Chaudhuri, "Databases for research on recognition of handwritten characters of Indian scripts", In Proc. of the 8th Int. Conf. on Document Analysis and Recognition (ICDAR-2005), Seoul, Korea, vol. II, page: 789-793, 2005.
NB: The whole database of handwritten Oriya numerals may be obtained free of cost for academic purposes by contacting through proper channel.