Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals
Abstract Given the vast range of factors, including shape, size, skew, and orientation of handwritten numerals, their machine-based recognition is a difficult challenge for researchers in the pattern recognition field. Due to the abundance of curves and resembling shapes of the symbols, the recognit...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-07-01
|
| Series: | Journal of Engineering and Applied Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s44147-023-00252-2 |
| _version_ | 1797774134253453312 |
|---|---|
| author | Danveer Rajpal Akhil Ranjan Garg |
| author_facet | Danveer Rajpal Akhil Ranjan Garg |
| author_sort | Danveer Rajpal |
| collection | DOAJ |
| description | Abstract Given the vast range of factors, including shape, size, skew, and orientation of handwritten numerals, their machine-based recognition is a difficult challenge for researchers in the pattern recognition field. Due to the abundance of curves and resembling shapes of the symbols, the recognition of Devnagari numerals can leverage the difficulty level of the recognition. The suggested low-classification-cost method for obtaining fine features from given numeral images used benchmark deep learning models, VGG-16Net, VGG-19Net, ResNet-50, and Inception-v3, to address these issues. Principal component analysis, a powerful dimensionality reduction method, was used to efficiently reduce the number of dimensions in the information that pre-trained deep convolutional neural network models provided. The method for improving recognition accuracy by fusing features was provided in the scheme. A machine learning algorithm: support vector machine was employed for the recognition task due to its capacity to distinguish between patterns belonging to distinct classes. The system was able to obtain a recognition accuracy of 99.72% and was effective in demonstrating the importance of ensemble machine learning and deep learning approaches. |
| first_indexed | 2024-03-12T22:16:34Z |
| format | Article |
| id | doaj.art-1ef59a9efec04a99ba92747271938f12 |
| institution | Directory Open Access Journal |
| issn | 1110-1903 2536-9512 |
| language | English |
| last_indexed | 2024-03-12T22:16:34Z |
| publishDate | 2023-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Engineering and Applied Science |
| spelling | doaj.art-1ef59a9efec04a99ba92747271938f122023-07-23T11:15:47ZengSpringerOpenJournal of Engineering and Applied Science1110-19032536-95122023-07-0170112110.1186/s44147-023-00252-2Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numeralsDanveer Rajpal0Akhil Ranjan Garg1Department of Electrical Engineering, M.B.M. UniversityDepartment of Electrical Engineering, M.B.M. UniversityAbstract Given the vast range of factors, including shape, size, skew, and orientation of handwritten numerals, their machine-based recognition is a difficult challenge for researchers in the pattern recognition field. Due to the abundance of curves and resembling shapes of the symbols, the recognition of Devnagari numerals can leverage the difficulty level of the recognition. The suggested low-classification-cost method for obtaining fine features from given numeral images used benchmark deep learning models, VGG-16Net, VGG-19Net, ResNet-50, and Inception-v3, to address these issues. Principal component analysis, a powerful dimensionality reduction method, was used to efficiently reduce the number of dimensions in the information that pre-trained deep convolutional neural network models provided. The method for improving recognition accuracy by fusing features was provided in the scheme. A machine learning algorithm: support vector machine was employed for the recognition task due to its capacity to distinguish between patterns belonging to distinct classes. The system was able to obtain a recognition accuracy of 99.72% and was effective in demonstrating the importance of ensemble machine learning and deep learning approaches.https://doi.org/10.1186/s44147-023-00252-2Deep convolutional neural networksDeep learningDimensionality reductionFeature optimizationFeature separationInception-v3 |
| spellingShingle | Danveer Rajpal Akhil Ranjan Garg Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals Journal of Engineering and Applied Science Deep convolutional neural networks Deep learning Dimensionality reduction Feature optimization Feature separation Inception-v3 |
| title | Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals |
| title_full | Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals |
| title_fullStr | Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals |
| title_full_unstemmed | Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals |
| title_short | Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals |
| title_sort | ensemble of deep learning and machine learning approach for classification of handwritten hindi numerals |
| topic | Deep convolutional neural networks Deep learning Dimensionality reduction Feature optimization Feature separation Inception-v3 |
| url | https://doi.org/10.1186/s44147-023-00252-2 |
| work_keys_str_mv | AT danveerrajpal ensembleofdeeplearningandmachinelearningapproachforclassificationofhandwrittenhindinumerals AT akhilranjangarg ensembleofdeeplearningandmachinelearningapproachforclassificationofhandwrittenhindinumerals |