Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images
Under-water sensing and image processing play major roles in oceanic scientific studies. One of the related challenges is that the absorption and scattering of light in underwater settings degrades the quality of the imaging. The major drawbacks of underwater imaging are color distortion, low contra...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/19/2742 |
| _version_ | 1797515676536012800 |
|---|---|
| author | Aswathy K. Cherian Eswaran Poovammal Ninan Sajeeth Philip Kadiyala Ramana Saurabh Singh In-Ho Ra |
| author_facet | Aswathy K. Cherian Eswaran Poovammal Ninan Sajeeth Philip Kadiyala Ramana Saurabh Singh In-Ho Ra |
| author_sort | Aswathy K. Cherian |
| collection | DOAJ |
| description | Under-water sensing and image processing play major roles in oceanic scientific studies. One of the related challenges is that the absorption and scattering of light in underwater settings degrades the quality of the imaging. The major drawbacks of underwater imaging are color distortion, low contrast, and loss of detail (especially edge information). The paper proposes a method to address these issues by de-noising and increasing the resolution of the image using a model network trained on similar data. The network extracts frames from a video and filters them with a trigonometric–Gaussian filter to eliminate the noise in the image. It then applies contrast limited adaptive histogram equalization (CLAHE) to improvise the image contrast, and finally enhances the image resolution. Experimental results show that the proposed method could effectively produce enhanced images from degraded underwater images. |
| first_indexed | 2024-03-10T06:48:39Z |
| format | Article |
| id | doaj.art-d8b04c6da1e94ae2b7bc95fd829b4982 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T06:48:39Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-d8b04c6da1e94ae2b7bc95fd829b49822023-11-22T17:01:58ZengMDPI AGWater2073-44412021-10-011319274210.3390/w13192742Deep Learning Based Filtering Algorithm for Noise Removal in Underwater ImagesAswathy K. Cherian0Eswaran Poovammal1Ninan Sajeeth Philip2Kadiyala Ramana3Saurabh Singh4In-Ho Ra5School of Computing, SRM Institute of Science and Technology, Chennai 602302, IndiaSchool of Computing, SRM Institute of Science and Technology, Chennai 602302, IndiaInter University Center for Astronomy and Astrophysics, Pune 411007, IndiaDepartment of Artificial Intelligence & Data Science, Annamacharya Institute of Technology and Sciences, Rajampet 516115, IndiaDepartment of Industrial and System Engineering, Dongguk University, Seoul 04620, KoreaSchool of Computer, Information and Communication Engineering, Kunsan National University, Gunsan 54150, KoreaUnder-water sensing and image processing play major roles in oceanic scientific studies. One of the related challenges is that the absorption and scattering of light in underwater settings degrades the quality of the imaging. The major drawbacks of underwater imaging are color distortion, low contrast, and loss of detail (especially edge information). The paper proposes a method to address these issues by de-noising and increasing the resolution of the image using a model network trained on similar data. The network extracts frames from a video and filters them with a trigonometric–Gaussian filter to eliminate the noise in the image. It then applies contrast limited adaptive histogram equalization (CLAHE) to improvise the image contrast, and finally enhances the image resolution. Experimental results show that the proposed method could effectively produce enhanced images from degraded underwater images.https://www.mdpi.com/2073-4441/13/19/2742bilateral filterCLAHEimage reconstructionimage resolutiontrigonometric–Gaussian filter |
| spellingShingle | Aswathy K. Cherian Eswaran Poovammal Ninan Sajeeth Philip Kadiyala Ramana Saurabh Singh In-Ho Ra Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images Water bilateral filter CLAHE image reconstruction image resolution trigonometric–Gaussian filter |
| title | Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images |
| title_full | Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images |
| title_fullStr | Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images |
| title_full_unstemmed | Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images |
| title_short | Deep Learning Based Filtering Algorithm for Noise Removal in Underwater Images |
| title_sort | deep learning based filtering algorithm for noise removal in underwater images |
| topic | bilateral filter CLAHE image reconstruction image resolution trigonometric–Gaussian filter |
| url | https://www.mdpi.com/2073-4441/13/19/2742 |
| work_keys_str_mv | AT aswathykcherian deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages AT eswaranpoovammal deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages AT ninansajeethphilip deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages AT kadiyalaramana deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages AT saurabhsingh deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages AT inhora deeplearningbasedfilteringalgorithmfornoiseremovalinunderwaterimages |