Deep learning based large scale handwritten Devanagari character recognition
By Shailesh Acharya, Ashok Kumar Pant, Prashnna Kumar Gyawali. 2015
190 citations recorded by the source corpus.
In this paper, we introduce a new public image dataset for Devanagari script: Devanagari Handwritten Character Dataset (DHCD). Our dataset consists of 92 thousand images of 46 different classes of characters of Devanagari script segmented from handwritten documents. We also explore the challenges in recognition of Devanagari characters. Along with the dataset, we also propose a deep learning architecture for recognition of those characters. Deep Convolutional Neural Network (CNN) have shown superior results to traditional shallow networks in many recognition tasks. Keeping distance with the regular approach of character recognition by Deep CNN, we focus the use of Dropout and dataset increment approach to improve test accuracy. By implementing these techniques in Deep CNN, we were able to increase test accuracy by nearly 1 percent. The proposed architecture scored highest test accuracy of 98.47% on our dataset.
Subfields: Computer Vision and Pattern Recognition, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Alexander Rainer Tassilo Gepperth
- Antonio Carta
- Davide Bacciu
- Andrea Cossu
- Benedikt Pfülb
- Joost van de Weijer
- Marc Masana
- Martin Mundt
In Media Technology
Citations in the corpus
- A comprehensive, application-oriented study of catastrophic forgetting in DNNs (2019, background): “Devanagari (Acharya, 2015) contains gray scale images of Devanagari handwritten letters.”
- Gradient-based training of Gaussian Mixture Models in High-Dimensional Spaces (2019, methodology): “The Devanagari (Acharya et al., 2015) dataset include gray scale images of handwritten Devanagari letters with a resolution of 32×32 pixels – the first 10 classes are selected.”
- Continual Learning with Gated Incremental Memories for sequential data processing (2020, background): “Devanagari is a dataset composed of images of handwritten characters belonging to 46 different classes [31].”