Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements
The broad application area and accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of characters may increase the difficulty level. Deep convolutional...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10128136/ |
| _version_ | 1827940626687066112 |
|---|---|
| author | Danveer Rajpal Akhil Ranjan Garg |
| author_facet | Danveer Rajpal Akhil Ranjan Garg |
| author_sort | Danveer Rajpal |
| collection | DOAJ |
| description | The broad application area and accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of characters may increase the difficulty level. Deep convolutional neural network (DCNN) models have been successful in solving pattern recognition problems, but at the expense of a considerable number of trainable parameters and heavy computational loads. The proposed work addresses these problems by using the shifted window (SWIN) transformer method to recognize handwritten Devanagari numerals for the first time. In the presented model, the SWIN transformer is finely tuned to withstand popular DCNN models, such as VGG-16Net, ResNet-50, and DenseNet-121, in terms of recognition accuracy, space requirement, and computational complexity. The model successfully attained a recognition accuracy of 99.20% with only 0.218 million trainable parameters and 0.0912 giga floating-point operations per second (FLOPs). This indicates the validity and soundness of the proposed model for recognizing handwritten Devanagari numerals. |
| first_indexed | 2024-03-13T09:12:20Z |
| format | Article |
| id | doaj.art-90f05103769145329ce12ea2eca55038 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T09:12:20Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-90f05103769145329ce12ea2eca550382023-05-26T23:00:54ZengIEEEIEEE Access2169-35362023-01-0111495304953910.1109/ACCESS.2023.327739210128136Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space RequirementsDanveer Rajpal0https://orcid.org/0000-0003-0622-9853Akhil Ranjan Garg1https://orcid.org/0000-0003-1778-2718Department of Electrical Engineering, MBM University, Jodhpur, IndiaDepartment of Electrical Engineering, MBM University, Jodhpur, IndiaThe broad application area and accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of characters may increase the difficulty level. Deep convolutional neural network (DCNN) models have been successful in solving pattern recognition problems, but at the expense of a considerable number of trainable parameters and heavy computational loads. The proposed work addresses these problems by using the shifted window (SWIN) transformer method to recognize handwritten Devanagari numerals for the first time. In the presented model, the SWIN transformer is finely tuned to withstand popular DCNN models, such as VGG-16Net, ResNet-50, and DenseNet-121, in terms of recognition accuracy, space requirement, and computational complexity. The model successfully attained a recognition accuracy of 99.20% with only 0.218 million trainable parameters and 0.0912 giga floating-point operations per second (FLOPs). This indicates the validity and soundness of the proposed model for recognizing handwritten Devanagari numerals.https://ieeexplore.ieee.org/document/10128136/Computational complexityDCNNdevanagari numeralsDenseNet-121ResNet-50shifted window transformer |
| spellingShingle | Danveer Rajpal Akhil Ranjan Garg Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements IEEE Access Computational complexity DCNN devanagari numerals DenseNet-121 ResNet-50 shifted window transformer |
| title | Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements |
| title_full | Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements |
| title_fullStr | Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements |
| title_full_unstemmed | Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements |
| title_short | Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements |
| title_sort | deep learning model for recognition of handwritten devanagari numerals with low computational complexity and space requirements |
| topic | Computational complexity DCNN devanagari numerals DenseNet-121 ResNet-50 shifted window transformer |
| url | https://ieeexplore.ieee.org/document/10128136/ |
| work_keys_str_mv | AT danveerrajpal deeplearningmodelforrecognitionofhandwrittendevanagarinumeralswithlowcomputationalcomplexityandspacerequirements AT akhilranjangarg deeplearningmodelforrecognitionofhandwrittendevanagarinumeralswithlowcomputationalcomplexityandspacerequirements |