Name
Abstract | ||
|---|---|---|
Handwritten digit recognition is still considered as a difficult task because of the large variability of the digits shapes written by individuals. A lot of work have been done towards digit identification with excellent performance but mostly these works have been made focusing on digits written in a particular script. Hence, in a multilingual country like India, where different scripts are prevalent, methods which recognise numerals written in a single script may not always serve the purpose. To address this issue, we propose a script invariant handwritten digit recognition scheme in this paper. A novel feature extraction technique named as quadrangular transition count has been introduced. Experimentations performed using five conventional classifiers advocate that multi layer perceptron (MLP) is best among them which yields recognition accuracies of 98.33%, 97.85%, 96.72% and 95.35% on four popularly used scripts of the world namely, Arabic, Bangla, Devanagari, and Roman respectively. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1504/IJCVR.2018.095005 | IJCVR |
Field | DocType | Volume |
Devanagari,Pattern recognition,Computer science,Numerical digit,Speech recognition,Feature extraction,Bengali,Latin script,Multilayer perceptron,Artificial intelligence,Numeral system,Arabic script | Journal | 8 |
Issue | Citations | PageRank |
5 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Pawan Kumar Singh | 1 | 57 | 14.89 |
| Supratim Das | 2 | 1 | 2.08 |
| Ram Sarkar | 3 | 420 | 68.85 |
| Mita Nasipuri | 4 | 725 | 107.01 |