A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters

The recognition of Indian and Arabic handwriting is drawing increasing attention in recent years. To test the promise of existing handwritten numeral recognition methods and provide new benchmarks for future research, this paper presents some results of handwritten Bangla and Farsi numeral recognition on binary and gray-scale images. On proper pre-processing, feature extraction and classification, we achieved very high accuracies on three databases: ISI Bangla numerals, CENPARMI Farsi numerals, and IFHCDB Farsi numerals. The benefit of recognition on gray-scale images is justified.