Abstract | ||
---|---|---|
Numeral recognition is an important preliminary step for optical character recognition, document understanding and others. Deep learning based numeral recognition models have achieved huge popularity among the researchers around the world since last few years. Several convolutional neural network (CNN) based architectures have been proposed and many of those have achieved state-of-the-art results in numeral recognition. In this paper, we have explored CNN based architectures for handwritten Arabic numeral recognition. We have also developed a handwritten Arabic numerals dataset using various morphological operations on an existing dataset thus increasing the size of the dataset from 3000 to 72,000 images. A modification of previously proposed CNN architecture has given us an accuracy of 98.91% and our proposed architecture has produced 99.76%, which is comparable to state-of-the-art results found in the domain of handwritten Arabic numeral recognition. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s12652-020-01901-7 | JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING |
Keywords | DocType | Volume |
OCR, Deep learning, CNN, Handwritten numeral recognition, Arabic numeral | Journal | 11 |
Issue | ISSN | Citations |
11 | 1868-5137 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pratik Ahamed | 1 | 0 | 0.34 |
Soumyadeep Kundu | 2 | 9 | 3.22 |
Tauseef Khan | 3 | 0 | 0.34 |
Vikrant Bhateja | 4 | 0 | 0.34 |
Ram Sarkar | 5 | 420 | 68.85 |
Ayatullah Faruk Mollah | 6 | 33 | 8.59 |