Advancements in handwritten Devanagari character recognition: a study on transfer learning and VGG16 algorithm

• Published in: Discover applied sciences Vol. 6; no. 12; pp. 623 - 15
• Main Authors: Sharma, Chetan, Sharma, Shamneesh, Sakshi, Chen, Hsin-Yuan
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 19.11.2024; Springer Nature B.V; Springer
• Subjects: Accuracy; Algorithms; Ancient languages; Applied and Technical Physics; Artificial neural networks; Character recognition; Chemistry/Food Science; Classification; CNN; Consonants (speech); Datasets; Deep learning; Devanagari; Earth Sciences; Education; Engineering; Environment; Handwriting; Handwriting recognition; Image enhancement; Language; Literature reviews; Machine learning; Materials Science; Neural networks; Postal & delivery services; Sanskrit; Support vector machines; Transfer learning; VGG16; Writers; Writing; India; Deep learning; CNN; Devanagari; VGG16; Classification; Machine learning

This study aims to create a system for recognizing handwritten Devanagari letters using deep neural networks (DNNs) for accurate character identification. The research utilizes explicitly transfer learning techniques in combination with the VGG16 convolutional neural network (CNN) model. The authors...