Subhashchandra Desai
Papers
1
Total Citations
3
H-Index
1
About
Subhashchandra Desai is a leading researcher in the field of pattern recognition and deep learning, with a specialized focus on handwritten character recognition for Indian scripts. His most notable contribution is the development of a layer-wise training methodology for deep convolutional neural networks, specifically applied to handwritten Hindi character recognition. This innovative approach addresses the challenges of training deep networks on complex, highly variable script datasets, achieving superior accuracy in distinguishing the intricate shapes of Devanagari characters. Desai’s work has significant real-world implications, particularly in assistive technologies for visually impaired users, human-robot interaction, and automated data entry for business documents. His 2020 paper on this topic has garnered 3 citations, laying foundational groundwork for subsequent research in Indic script recognition. By tackling the unique complexities of Hindi handwriting—with its large character set and frequent cursive variations—Desai has advanced the broader field of optical character recognition for non-Latin scripts. His research continues to inspire new approaches in deep learning architectures and transfer learning for low-resource languages.
Research Focus
Key Achievements
Top Papers
- 1