TenzinNet for handwritten Tibetan numeral recognition

Title

TenzinNet for handwritten Tibetan numeral recognition

Creator

Kaldan T.; Vijayalakshmi A.

Description

Tibet is known for its enumerable collection of Nalanda based Buddhism manuscripts that need to be digitized for immortalization of the teachings of Buddha and various Buddhist scholars. Handwritten Tibetan numeral recognition is relatively unexplored as compared to Roman and Chinese numerals. Recognition of handwritten documents for digitalization has been under study from past many years. This work proposes a novel model using convolutional neural networks architecture named as TenzinNet to recognize handwritten Tibetan numerals. TenzinNet achieved an accuracy of 90.76% in recognizing Tibetan numerals using the proposed model. 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

Source

International Journal of Information Technology (Singapore), Vol-13, No. 4, pp. 1679-1682.

Date

2021-01-01

Publisher

Springer Science and Business Media B.V.

Subject

Character recognition; Convolutional neural network (CNN); Handwritten digit recognition; Handwritten Tibetan numeral; Machine learning

Coverage

Kaldan T., Christ University, Bengaluru, India; Vijayalakshmi A., Christ University, Bengaluru, India

Rights

Restricted Access

Relation

ISSN: 25112104

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1007/s41870-021-00711-0

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85106401142&doi=10.1007%2fs41870-021-00711-0&partnerID=40&md5=8b20d3f50f75f471a5ebc73d90a82c47