Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments
Removal Poisson noise poses a very challenging technical issue because it is difficult to capture noise characteristics. This induces from the fact that Poisson noises from different sources affect each image pixel proportional to the pixel level. This paper addresses a new image denoising method fo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9085404/ |
| _version_ | 1819159263042338816 |
|---|---|
| author | Wuttipong Kumwilaisak Teerawat Piriyatharawet Pongsak Lasang Nattanun Thatphithakkul |
| author_facet | Wuttipong Kumwilaisak Teerawat Piriyatharawet Pongsak Lasang Nattanun Thatphithakkul |
| author_sort | Wuttipong Kumwilaisak |
| collection | DOAJ |
| description | Removal Poisson noise poses a very challenging technical issue because it is difficult to capture noise characteristics. This induces from the fact that Poisson noises from different sources affect each image pixel proportional to the pixel level. This paper addresses a new image denoising method for removing Poisson noise based on the Deep Convolutional Neural and Multi-directional Long-Short Term Memory Networks. The architecture of the proposed network contains some Convolutional Neural Network (CNN) layers and multi-directional Long-Short Term Memory (LSTM) layers. CNN layers are responsible to extract image features and to estimate some noise bases existed in images. The multi-directional LSTM layers are used to effectively capture and learn the statistics of residual noise components, which possess long-range correlations and appear sparse in the spatial domain. Moreover, designing deep learning models for image denoising involves several hyperparameters such as a number of layers. To select proper hyperparameters, it is beneficial to investigate what is the best image denoising performance we can achieve under different model complexities. Moreover knowing and realizing how far the employing image denoising algorithm can do to the optimal result makes us possible to design the efficient image denoising algorithm. We utilize the Blahut-Arimoto algorithm to derive numerically distortion-mutual information function of image denoising algorithm. The derived function serves as the distortion lower bound given the mutual information between the original image and the denoised image. Based on the knowledge of distortion-mutual information function, we can decide how deep the CNN layers should be deployed in our image denoising algorithm before applying the multi-directional LSTM layers. From our experiments, the proposed image denoising algorithm can outperform other algorithms in both subjective and objective qualities. |
| first_indexed | 2024-12-22T16:37:46Z |
| format | Article |
| id | doaj.art-6a767705039a4d6ab7836b6aa1fb595a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T16:37:46Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6a767705039a4d6ab7836b6aa1fb595a2022-12-21T18:19:54ZengIEEEIEEE Access2169-35362020-01-018869988701010.1109/ACCESS.2020.29919889085404Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise EnvironmentsWuttipong Kumwilaisak0https://orcid.org/0000-0002-2957-6084Teerawat Piriyatharawet1Pongsak Lasang2Nattanun Thatphithakkul3Department of Electronics and Telecommunication Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandDepartment of Electronics and Telecommunication Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandPanasonic Research and Development Center Singapore (PRDCSG), SingaporeNational Science and Technology Development Agency, Pathum Thani, ThailandRemoval Poisson noise poses a very challenging technical issue because it is difficult to capture noise characteristics. This induces from the fact that Poisson noises from different sources affect each image pixel proportional to the pixel level. This paper addresses a new image denoising method for removing Poisson noise based on the Deep Convolutional Neural and Multi-directional Long-Short Term Memory Networks. The architecture of the proposed network contains some Convolutional Neural Network (CNN) layers and multi-directional Long-Short Term Memory (LSTM) layers. CNN layers are responsible to extract image features and to estimate some noise bases existed in images. The multi-directional LSTM layers are used to effectively capture and learn the statistics of residual noise components, which possess long-range correlations and appear sparse in the spatial domain. Moreover, designing deep learning models for image denoising involves several hyperparameters such as a number of layers. To select proper hyperparameters, it is beneficial to investigate what is the best image denoising performance we can achieve under different model complexities. Moreover knowing and realizing how far the employing image denoising algorithm can do to the optimal result makes us possible to design the efficient image denoising algorithm. We utilize the Blahut-Arimoto algorithm to derive numerically distortion-mutual information function of image denoising algorithm. The derived function serves as the distortion lower bound given the mutual information between the original image and the denoised image. Based on the knowledge of distortion-mutual information function, we can decide how deep the CNN layers should be deployed in our image denoising algorithm before applying the multi-directional LSTM layers. From our experiments, the proposed image denoising algorithm can outperform other algorithms in both subjective and objective qualities.https://ieeexplore.ieee.org/document/9085404/Poisson noisedeep learningconvolutional neural networkmulti-directional LSTM networkdistortion-mutual information function |
| spellingShingle | Wuttipong Kumwilaisak Teerawat Piriyatharawet Pongsak Lasang Nattanun Thatphithakkul Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments IEEE Access Poisson noise deep learning convolutional neural network multi-directional LSTM network distortion-mutual information function |
| title | Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments |
| title_full | Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments |
| title_fullStr | Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments |
| title_full_unstemmed | Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments |
| title_short | Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments |
| title_sort | image denoising with deep convolutional neural and multi directional long short term memory networks under poisson noise environments |
| topic | Poisson noise deep learning convolutional neural network multi-directional LSTM network distortion-mutual information function |
| url | https://ieeexplore.ieee.org/document/9085404/ |
| work_keys_str_mv | AT wuttipongkumwilaisak imagedenoisingwithdeepconvolutionalneuralandmultidirectionallongshorttermmemorynetworksunderpoissonnoiseenvironments AT teerawatpiriyatharawet imagedenoisingwithdeepconvolutionalneuralandmultidirectionallongshorttermmemorynetworksunderpoissonnoiseenvironments AT pongsaklasang imagedenoisingwithdeepconvolutionalneuralandmultidirectionallongshorttermmemorynetworksunderpoissonnoiseenvironments AT nattanunthatphithakkul imagedenoisingwithdeepconvolutionalneuralandmultidirectionallongshorttermmemorynetworksunderpoissonnoiseenvironments |