Detection of Gaussian noise and its level using deep convolutonal neural network
This study presents a Convolutional Neural Network (CNN) model to effectively recognize the presence of Gaussian noise and its level in images. The existing denoising approaches are mostly based on an assumption that the images to be processed are corrupted with noises. This work, on the other...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/18531/1/Manuscript.pdf |
| _version_ | 1796960507427553280 |
|---|---|
| author | Joon, H.C. Hui, Y.K. Foo, C.S. Chee, O.C. |
| author_facet | Joon, H.C. Hui, Y.K. Foo, C.S. Chee, O.C. |
| author_sort | Joon, H.C. |
| collection | UM |
| description | This study presents a Convolutional Neural
Network (CNN) model to effectively recognize the presence of
Gaussian noise and its level in images. The existing denoising
approaches are mostly based on an assumption that the images to
be processed are corrupted with noises. This work, on the other
hand, aims to intelligently evaluate if an image is corrupted, and
to which level it is degraded, before applying denoising
algorithms. We used 12000 and 3000 standard test images for
training and testing purposes, respectively. Different noise levels
are introduced to these images. The overall accuracy of 74.7% in
classifying 10 classes of noise levels are obtained. Our
experiments and results have proven that this model is capable of
performing Gaussian noise detection and its noise level
classification. |
| first_indexed | 2024-03-06T05:45:39Z |
| format | Conference or Workshop Item |
| id | um.eprints-18531 |
| institution | Universiti Malaya |
| language | English |
| last_indexed | 2024-03-06T05:45:39Z |
| publishDate | 2017 |
| record_format | dspace |
| spelling | um.eprints-185312018-01-18T06:53:04Z http://eprints.um.edu.my/18531/ Detection of Gaussian noise and its level using deep convolutonal neural network Joon, H.C. Hui, Y.K. Foo, C.S. Chee, O.C. TK Electrical engineering. Electronics Nuclear engineering This study presents a Convolutional Neural Network (CNN) model to effectively recognize the presence of Gaussian noise and its level in images. The existing denoising approaches are mostly based on an assumption that the images to be processed are corrupted with noises. This work, on the other hand, aims to intelligently evaluate if an image is corrupted, and to which level it is degraded, before applying denoising algorithms. We used 12000 and 3000 standard test images for training and testing purposes, respectively. Different noise levels are introduced to these images. The overall accuracy of 74.7% in classifying 10 classes of noise levels are obtained. Our experiments and results have proven that this model is capable of performing Gaussian noise detection and its noise level classification. 2017 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.um.edu.my/18531/1/Manuscript.pdf Joon, H.C. and Hui, Y.K. and Foo, C.S. and Chee, O.C. (2017) Detection of Gaussian noise and its level using deep convolutonal neural network. In: 2017 IEEE Region 10 Conference (TENCON), 05-08 November 2017, Penang, Malaysia. |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Joon, H.C. Hui, Y.K. Foo, C.S. Chee, O.C. Detection of Gaussian noise and its level using deep convolutonal neural network |
| title | Detection of Gaussian noise and its level using
deep convolutonal neural network |
| title_full | Detection of Gaussian noise and its level using
deep convolutonal neural network |
| title_fullStr | Detection of Gaussian noise and its level using
deep convolutonal neural network |
| title_full_unstemmed | Detection of Gaussian noise and its level using
deep convolutonal neural network |
| title_short | Detection of Gaussian noise and its level using
deep convolutonal neural network |
| title_sort | detection of gaussian noise and its level using deep convolutonal neural network |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.um.edu.my/18531/1/Manuscript.pdf |
| work_keys_str_mv | AT joonhc detectionofgaussiannoiseanditslevelusingdeepconvolutonalneuralnetwork AT huiyk detectionofgaussiannoiseanditslevelusingdeepconvolutonalneuralnetwork AT foocs detectionofgaussiannoiseanditslevelusingdeepconvolutonalneuralnetwork AT cheeoc detectionofgaussiannoiseanditslevelusingdeepconvolutonalneuralnetwork |