Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models
This paper aims to increase the accuracy of Kazakh handwriting text recognition (KHTR) using the generative adversarial network (GAN), where a handwriting word image generator and an image quality discriminator are constructed. In order to obtain a high-quality image of handwritten text, the multipl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/9/5677 |
| _version_ | 1797602954121838592 |
|---|---|
| author | Arman Yeleussinov Yedilkhan Amirgaliyev Lyailya Cherikbayeva |
| author_facet | Arman Yeleussinov Yedilkhan Amirgaliyev Lyailya Cherikbayeva |
| author_sort | Arman Yeleussinov |
| collection | DOAJ |
| description | This paper aims to increase the accuracy of Kazakh handwriting text recognition (KHTR) using the generative adversarial network (GAN), where a handwriting word image generator and an image quality discriminator are constructed. In order to obtain a high-quality image of handwritten text, the multiple losses are intended to encourage the generator to learn the structural properties of the texts. In this case, the quality discriminator is trained on the basis of the relativistic loss function. Based on the proposed structure, the resulting document images not only preserve texture details but also generate different writer styles, which provides better OCR performance in public databases. With a self-created dataset, images of different types of handwriting styles were obtained, which will be used when training the network. The proposed approach allows for a character error rate (CER) of 11.15% and a word error rate (WER) of 25.65%. |
| first_indexed | 2024-03-11T04:22:53Z |
| format | Article |
| id | doaj.art-0f4f2f56daf04c9a8c09e5f2a0cda5a9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T04:22:53Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0f4f2f56daf04c9a8c09e5f2a0cda5a92023-11-17T22:37:24ZengMDPI AGApplied Sciences2076-34172023-05-01139567710.3390/app13095677Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN ModelsArman Yeleussinov0Yedilkhan Amirgaliyev1Lyailya Cherikbayeva2Faculty of Information Technology, Department of Computer Science, Al Farabi Kazakh National University, Almaty 050010, KazakhstanInstitute of Information and Computational Technologies, Almaty 050010, KazakhstanFaculty of Information Technology, Department of Computer Science, Al Farabi Kazakh National University, Almaty 050010, KazakhstanThis paper aims to increase the accuracy of Kazakh handwriting text recognition (KHTR) using the generative adversarial network (GAN), where a handwriting word image generator and an image quality discriminator are constructed. In order to obtain a high-quality image of handwritten text, the multiple losses are intended to encourage the generator to learn the structural properties of the texts. In this case, the quality discriminator is trained on the basis of the relativistic loss function. Based on the proposed structure, the resulting document images not only preserve texture details but also generate different writer styles, which provides better OCR performance in public databases. With a self-created dataset, images of different types of handwriting styles were obtained, which will be used when training the network. The proposed approach allows for a character error rate (CER) of 11.15% and a word error rate (WER) of 25.65%.https://www.mdpi.com/2076-3417/13/9/5677optical character recognitiongenerative adversarial networkcharacter error rateword error rate |
| spellingShingle | Arman Yeleussinov Yedilkhan Amirgaliyev Lyailya Cherikbayeva Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models Applied Sciences optical character recognition generative adversarial network character error rate word error rate |
| title | Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models |
| title_full | Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models |
| title_fullStr | Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models |
| title_full_unstemmed | Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models |
| title_short | Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models |
| title_sort | improving ocr accuracy for kazakh handwriting recognition using gan models |
| topic | optical character recognition generative adversarial network character error rate word error rate |
| url | https://www.mdpi.com/2076-3417/13/9/5677 |
| work_keys_str_mv | AT armanyeleussinov improvingocraccuracyforkazakhhandwritingrecognitionusingganmodels AT yedilkhanamirgaliyev improvingocraccuracyforkazakhhandwritingrecognitionusingganmodels AT lyailyacherikbayeva improvingocraccuracyforkazakhhandwritingrecognitionusingganmodels |