DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters
Many problems can reduce handwritten character recognition performance, such as image degradation, light conditions, low-resolution images, and even the quality of the capture devices. However, in this research, we have focused on the noise in the character images that could decrease the accuracy of...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9866776/ |
| _version_ | 1818473495074439168 |
|---|---|
| author | Sarayut Gonwirat Olarik Surinta |
| author_facet | Sarayut Gonwirat Olarik Surinta |
| author_sort | Sarayut Gonwirat |
| collection | DOAJ |
| description | Many problems can reduce handwritten character recognition performance, such as image degradation, light conditions, low-resolution images, and even the quality of the capture devices. However, in this research, we have focused on the noise in the character images that could decrease the accuracy of handwritten character recognition. Many types of noise penalties influence the recognition performance, for example, low resolution, Gaussian noise, low contrast, and blur. First, this research proposes a method that learns from the noisy handwritten character images and synthesizes clean character images using the robust deblur generative adversarial network (DeblurGAN). Second, we combine the DeblurGAN architecture with a convolutional neural network (CNN), called DeblurGAN-CNN. Subsequently, two state-of-the-art CNN architectures are combined with DeblurGAN, namely DeblurGAN-DenseNet121 and DeblurGAN-MobileNetV2, to address many noise problems and enhance the recognition performance of the handwritten character images. Finally, the DeblurGAN-CNN could transform the noisy characters to the new clean characters and recognize clean characters simultaneously. We have evaluated and compared the experimental results of the proposed DeblurGAN-CNN architectures with the existing methods on four handwritten character datasets: n-THI-C68, n-MNIST, THI-C68, and THCC-67. For the n-THI-C68 dataset, the DeblurGAN-CNN achieved above 98% and outperformed the other existing methods. For the n-MNIST, the proposed DeblurGAN-CNN achieved an accuracy of 97.59% when the AWGN+Contrast noise method was applied to the handwritten digits. We have evaluated the DeblurGAN-CNN on the THCC-67 dataset. The result showed that the proposed DeblurGAN-CNN achieved an accuracy of 80.68%, which is significantly higher than the existing method, approximately 10%. |
| first_indexed | 2024-04-14T04:24:50Z |
| format | Article |
| id | doaj.art-18dc41c1f8ec4da29337d8bd6e706b52 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T04:24:50Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-18dc41c1f8ec4da29337d8bd6e706b522022-12-22T02:12:22ZengIEEEIEEE Access2169-35362022-01-0110901339014810.1109/ACCESS.2022.32015609866776DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten CharactersSarayut Gonwirat0https://orcid.org/0000-0001-7179-7510Olarik Surinta1https://orcid.org/0000-0002-0644-1435Department of Information Technology, Faculty of Informatics, Multi-Agent Intelligent Simulation Laboratory (MISL), Mahasarakham University, Mahasarakham, ThailandDepartment of Information Technology, Faculty of Informatics, Multi-Agent Intelligent Simulation Laboratory (MISL), Mahasarakham University, Mahasarakham, ThailandMany problems can reduce handwritten character recognition performance, such as image degradation, light conditions, low-resolution images, and even the quality of the capture devices. However, in this research, we have focused on the noise in the character images that could decrease the accuracy of handwritten character recognition. Many types of noise penalties influence the recognition performance, for example, low resolution, Gaussian noise, low contrast, and blur. First, this research proposes a method that learns from the noisy handwritten character images and synthesizes clean character images using the robust deblur generative adversarial network (DeblurGAN). Second, we combine the DeblurGAN architecture with a convolutional neural network (CNN), called DeblurGAN-CNN. Subsequently, two state-of-the-art CNN architectures are combined with DeblurGAN, namely DeblurGAN-DenseNet121 and DeblurGAN-MobileNetV2, to address many noise problems and enhance the recognition performance of the handwritten character images. Finally, the DeblurGAN-CNN could transform the noisy characters to the new clean characters and recognize clean characters simultaneously. We have evaluated and compared the experimental results of the proposed DeblurGAN-CNN architectures with the existing methods on four handwritten character datasets: n-THI-C68, n-MNIST, THI-C68, and THCC-67. For the n-THI-C68 dataset, the DeblurGAN-CNN achieved above 98% and outperformed the other existing methods. For the n-MNIST, the proposed DeblurGAN-CNN achieved an accuracy of 97.59% when the AWGN+Contrast noise method was applied to the handwritten digits. We have evaluated the DeblurGAN-CNN on the THCC-67 dataset. The result showed that the proposed DeblurGAN-CNN achieved an accuracy of 80.68%, which is significantly higher than the existing method, approximately 10%.https://ieeexplore.ieee.org/document/9866776/Handwritten character recognitiondenoising imagegenerative adversarial networkDeblurGANconvolutional neural network |
| spellingShingle | Sarayut Gonwirat Olarik Surinta DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters IEEE Access Handwritten character recognition denoising image generative adversarial network DeblurGAN convolutional neural network |
| title | DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters |
| title_full | DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters |
| title_fullStr | DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters |
| title_full_unstemmed | DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters |
| title_short | DeblurGAN-CNN: Effective Image Denoising and Recognition for Noisy Handwritten Characters |
| title_sort | deblurgan cnn effective image denoising and recognition for noisy handwritten characters |
| topic | Handwritten character recognition denoising image generative adversarial network DeblurGAN convolutional neural network |
| url | https://ieeexplore.ieee.org/document/9866776/ |
| work_keys_str_mv | AT sarayutgonwirat deblurgancnneffectiveimagedenoisingandrecognitionfornoisyhandwrittencharacters AT olariksurinta deblurgancnneffectiveimagedenoisingandrecognitionfornoisyhandwrittencharacters |