Object recognition from underwater Images using deep cnn approach
| dc.contributor.guide | Seldev Christopher | |
| dc.coverage.spatial | Object recognition from underwater Images using deep cnn approach | |
| dc.creator.researcher | Lyernisha S R | |
| dc.date.accessioned | 2024-05-31T04:57:10Z | |
| dc.date.available | 2024-05-31T04:57:10Z | |
| dc.date.awarded | 2024 | |
| dc.date.completed | 2024 | |
| dc.date.registered | ||
| dc.description.abstract | newline exploration, and underwater autonomous operation is becoming more and more essential to stay safe in the risky high-pressure deep-sea environment, because it is challenging to restore underwater images, the researcher is interested in light scattering and absorption phenomena to generate distortion in the images. newlineHowever, because of color distortion, noise, and dispersion, these methods have some difficulty recognizing underwater objects. Therefore, improving the underwater imagination is crucial for correctly identifying underwater things. The SSAG optimization-based deep CNN is developed in this research for image enhancement models to address this problem, the grouping behavior and adaptability of the guards and flocks, which serve as the search agents in the proposed optimization, are integrated to create the suggested social situation-aware guard optimization. | |
| dc.description.note | ||
| dc.format.accompanyingmaterial | DVD | |
| dc.format.dimensions | 21cm | |
| dc.format.extent | xvi,159p. | |
| dc.identifier.uri | http://hdl.handle.net/10603/568164 | |
| dc.language | English | |
| dc.publisher.institution | Faculty of Information and Communication Engineering | |
| dc.publisher.place | Chennai | |
| dc.publisher.university | Anna University | |
| dc.relation | p.141-158 | |
| dc.rights | university | |
| dc.source.university | University | |
| dc.subject.keyword | Computer Science | |
| dc.subject.keyword | Computer Science Information Systems | |
| dc.subject.keyword | Engineering and Technology | |
| dc.title | Object recognition from underwater Images using deep cnn approach | |
| dc.title.alternative | ||
| dc.type.degree | Ph.D. |
Files
Original bundle
1 - 5 of 11
Loading...
- Name:
- 01_title.pdf
- Size:
- 29.37 KB
- Format:
- Adobe Portable Document Format
- Description:
- Attached File
Loading...
- Name:
- 02_prelim pages.pdf
- Size:
- 538.48 KB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1