Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet
Automated recognition of handwritten characters and digits is a challenging task. Although a significant amount of literature exists for automatic recognition of handwritten characters of English and other major languages in the world, there exists a wide research gap due to lack of research for rec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9900315/ |
| _version_ | 1811229951721996288 |
|---|---|
| author | Aqsa Rasheed Nouman Ali Bushra Zafar Amsa Shabbir Muhammad Sajid Muhammad Tariq Mahmood |
| author_facet | Aqsa Rasheed Nouman Ali Bushra Zafar Amsa Shabbir Muhammad Sajid Muhammad Tariq Mahmood |
| author_sort | Aqsa Rasheed |
| collection | DOAJ |
| description | Automated recognition of handwritten characters and digits is a challenging task. Although a significant amount of literature exists for automatic recognition of handwritten characters of English and other major languages in the world, there exists a wide research gap due to lack of research for recognition of Urdu language. The variations in writing style, shape and size of individual characters and similarities with other characters add to the complexity for accurate classification of handwritten characters. Deep neural networks have emerged as a powerful technology for automated classification of character patters and object images. Although deep networks are known to provide remarkable results on large-scale datasets with millions of images, however the use of deep networks for small image datasets is still challenging. The purpose of this research is to present a classification framework for automatic recognition of handwritten Urdu character and digits with higher recognition accuracy by utilizing theory of transfer learning and pre-trained Convolution Neural Networks (CNN). The performance of transfer learning is evaluated in different ways: by using pre-trained AlexNet CNN model with Support Vector Machine (SVM) classifier, and fine-tuned AlexNet for extracting features and classification. We have fine-tuned AlexNet hyper-parameters to achieve higher accuracy and data augmentation is performed to avoid over-fitting. Experimental results and the quantitative comparisons demonstrate the effectiveness of the proposed research for recognition of handwritten characters and digits using fine-tuned AlexNet. The proposed research based on fine-tuned AlexNet outperforms the related state-of-the-art research thereby achieving a classification accuracy of 97.08%, 98.21%, 94.92% for urdu characters, digits and hybrid datasets respectively. The presented methods can be applied for research on Urdu characters and in diverse domains such as handwritten text image retrieval, reading postal addresses, bank’s cheque processing, preserving and digitization of manuscripts from old ages. |
| first_indexed | 2024-04-12T10:21:56Z |
| format | Article |
| id | doaj.art-cbdde443b2fc42d3a6c03fe614d586b3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T10:21:56Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-cbdde443b2fc42d3a6c03fe614d586b32022-12-22T03:37:04ZengIEEEIEEE Access2169-35362022-01-011010262910264510.1109/ACCESS.2022.32089599900315Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNetAqsa Rasheed0https://orcid.org/0000-0003-0775-836XNouman Ali1https://orcid.org/0000-0002-0721-201XBushra Zafar2https://orcid.org/0000-0002-8869-3037Amsa Shabbir3Muhammad Sajid4https://orcid.org/0000-0003-0020-1235Muhammad Tariq Mahmood5https://orcid.org/0000-0001-6814-3137Department of Software Engineering, Mirpur University of Science and Technology, Mirpur-AJK, PakistanDepartment of Software Engineering, Mirpur University of Science and Technology, Mirpur-AJK, PakistanDepartment of Computer Science, Government College University, Faisalabad, PakistanDepartment of Software Engineering, Mirpur University of Science and Technology, Mirpur-AJK, PakistanDepartment of Electrical Engineering, Mirpur University of Science and Technology, Mirpur-AJK, PakistanFuture Convergence Engineering, Korea University of Technology and Education, Cheonan, Republic of KoreaAutomated recognition of handwritten characters and digits is a challenging task. Although a significant amount of literature exists for automatic recognition of handwritten characters of English and other major languages in the world, there exists a wide research gap due to lack of research for recognition of Urdu language. The variations in writing style, shape and size of individual characters and similarities with other characters add to the complexity for accurate classification of handwritten characters. Deep neural networks have emerged as a powerful technology for automated classification of character patters and object images. Although deep networks are known to provide remarkable results on large-scale datasets with millions of images, however the use of deep networks for small image datasets is still challenging. The purpose of this research is to present a classification framework for automatic recognition of handwritten Urdu character and digits with higher recognition accuracy by utilizing theory of transfer learning and pre-trained Convolution Neural Networks (CNN). The performance of transfer learning is evaluated in different ways: by using pre-trained AlexNet CNN model with Support Vector Machine (SVM) classifier, and fine-tuned AlexNet for extracting features and classification. We have fine-tuned AlexNet hyper-parameters to achieve higher accuracy and data augmentation is performed to avoid over-fitting. Experimental results and the quantitative comparisons demonstrate the effectiveness of the proposed research for recognition of handwritten characters and digits using fine-tuned AlexNet. The proposed research based on fine-tuned AlexNet outperforms the related state-of-the-art research thereby achieving a classification accuracy of 97.08%, 98.21%, 94.92% for urdu characters, digits and hybrid datasets respectively. The presented methods can be applied for research on Urdu characters and in diverse domains such as handwritten text image retrieval, reading postal addresses, bank’s cheque processing, preserving and digitization of manuscripts from old ages.https://ieeexplore.ieee.org/document/9900315/Automated recognitionurdu HCR systemsCNNtransfer learningalexnetSVM |
| spellingShingle | Aqsa Rasheed Nouman Ali Bushra Zafar Amsa Shabbir Muhammad Sajid Muhammad Tariq Mahmood Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet IEEE Access Automated recognition urdu HCR systems CNN transfer learning alexnet SVM |
| title | Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet |
| title_full | Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet |
| title_fullStr | Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet |
| title_full_unstemmed | Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet |
| title_short | Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet |
| title_sort | handwritten urdu characters and digits recognition using transfer learning and augmentation with alexnet |
| topic | Automated recognition urdu HCR systems CNN transfer learning alexnet SVM |
| url | https://ieeexplore.ieee.org/document/9900315/ |
| work_keys_str_mv | AT aqsarasheed handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet AT noumanali handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet AT bushrazafar handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet AT amsashabbir handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet AT muhammadsajid handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet AT muhammadtariqmahmood handwrittenurducharactersanddigitsrecognitionusingtransferlearningandaugmentationwithalexnet |