Towards building a Bangla text recognition solution with a Multi-Headed CNN architecture

Bangla is among the ten most popular languages in the world by the number of speakers. The task of Bangla recognition is quite challenging than other languages because of the existence of graphemes of multiple single characters, and diacritics of vowels and consonants. The purpose of this study is to develop an innovative large-scale Bangla OCR solution based on character-level recognition. Two types of documents were used to test our method: handwritten and printed. In addition, our method was applied to the handwritten documents as well as three subdomains of the printed domain: computer-composed, letterpress, and typewritten documents using our proposed attention-based multi-headed CNN architecture. Extensive testing shows that our method provides state-of-the-art performance on both handwritten and printed texts.