Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition
The performance of any machine learning model largely depends on the type of input data provided. The higher the volume and variety of the data, the better the machine learning models get trained, thereby producing more accurate results. However, it is a challenging task to get high volume of data i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2022-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2022/6180701 |
| _version_ | 1826992966316589056 |
|---|---|
| author | Mamatarani Das Mrutyunjaya Panda Shreela Dash |
| author_facet | Mamatarani Das Mrutyunjaya Panda Shreela Dash |
| author_sort | Mamatarani Das |
| collection | DOAJ |
| description | The performance of any machine learning model largely depends on the type of input data provided. The higher the volume and variety of the data, the better the machine learning models get trained, thereby producing more accurate results. However, it is a challenging task to get high volume of data in some cases containing enough variety. Handwritten character recognition for Odia language is one of them. NITROHCS v1.0 for handwritten Odia characters and the ISI image database for handwritten Odia numerals are the standard Odia language datasets available for the research community. This paper shows the performance of five different machine learning models that uses a convolutional neural network to identify handwritten characters in response to handwritten datasets that are manipulated and expanded using several augmentation techniques to create variation and increase the volume of the data in the given dataset. These models, with the augmentation techniques discussed in the paper, even lead to a further increase in accuracy by approximately 1% across the models. The claims are supported by the results from the experiments done on the proposed convolutional neural network models on standard available Odia character and numeral data set. |
| first_indexed | 2024-04-11T03:49:53Z |
| format | Article |
| id | doaj.art-9cf601ea814f44878b521c3d55ca83b6 |
| institution | Directory Open Access Journal |
| issn | 1687-5699 |
| language | English |
| last_indexed | 2025-02-18T08:57:01Z |
| publishDate | 2022-01-01 |
| publisher | Hindawi Limited |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj.art-9cf601ea814f44878b521c3d55ca83b62024-11-02T23:54:17ZengHindawi LimitedAdvances in Multimedia1687-56992022-01-01202210.1155/2022/6180701Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character RecognitionMamatarani Das0Mrutyunjaya Panda1Shreela Dash2Utkal UniversityUtkal UniversitySilicon Institute of TechnologyThe performance of any machine learning model largely depends on the type of input data provided. The higher the volume and variety of the data, the better the machine learning models get trained, thereby producing more accurate results. However, it is a challenging task to get high volume of data in some cases containing enough variety. Handwritten character recognition for Odia language is one of them. NITROHCS v1.0 for handwritten Odia characters and the ISI image database for handwritten Odia numerals are the standard Odia language datasets available for the research community. This paper shows the performance of five different machine learning models that uses a convolutional neural network to identify handwritten characters in response to handwritten datasets that are manipulated and expanded using several augmentation techniques to create variation and increase the volume of the data in the given dataset. These models, with the augmentation techniques discussed in the paper, even lead to a further increase in accuracy by approximately 1% across the models. The claims are supported by the results from the experiments done on the proposed convolutional neural network models on standard available Odia character and numeral data set.http://dx.doi.org/10.1155/2022/6180701 |
| spellingShingle | Mamatarani Das Mrutyunjaya Panda Shreela Dash Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition Advances in Multimedia |
| title | Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition |
| title_full | Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition |
| title_fullStr | Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition |
| title_full_unstemmed | Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition |
| title_short | Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition |
| title_sort | enhancing the power of cnn using data augmentation techniques for odia handwritten character recognition |
| url | http://dx.doi.org/10.1155/2022/6180701 |
| work_keys_str_mv | AT mamataranidas enhancingthepowerofcnnusingdataaugmentationtechniquesforodiahandwrittencharacterrecognition AT mrutyunjayapanda enhancingthepowerofcnnusingdataaugmentationtechniquesforodiahandwrittencharacterrecognition AT shreeladash enhancingthepowerofcnnusingdataaugmentationtechniquesforodiahandwrittencharacterrecognition |