Underwater image restoration : super-resolution and deblurring via sparse representation and denoising by means of marine snow removal

Fahimeh Farhadifard

doi:10.18453/rosdok_id00002088

Fahimeh Farhadifard

Underwater image restoration : super-resolution and deblurring via sparse representation and denoising by means of marine snow removal

Universität Rostock, 2018

https://doi.org/10.18453/rosdok_id00002088

Abstract: Underwater imaging has been widely used as a tool in many fields, however, a major issue is the quality of the resulting images/videos. Due to the light's interaction with water and its constituents, the acquired underwater images/videos often suffer from a significant amount of scatter (blur, haze) and noise. In the light of these issues, this thesis considers problems of low-resolution, blurred and noisy underwater images and proposes several approaches to improve the quality of such images/video frames. Quantitative and qualitative experiments validate the success of proposed algorithms.

Dissertation Freier Zugang

Titel:

Underwater image restoration: super-resolution and deblurring via sparse representation and denoising by means of marine snow removal

Beteiligte Personen:

Fahimeh Farhadifard[VerfasserIn]
	1161750770
Bodo Urban , Prof. Dr. -Ing[AkademischeR BetreuerIn]
	132788357
	Rostock, Fraunhofer IGD
Uwe Freiherr von Lukas , Prof. Dr. -Ing[AkademischeR BetreuerIn]
	128388951
	Rostock, Fraunhofer IGD
Reinhard Koch , Prof. Dr. -Ing[AkademischeR BetreuerIn]
	1015521614
	Christian-Albrechts-Universitaet zu Kiel

Beteiligte Körperschaften:

Universität Rostock, Fakultät für Informatik und Elektrotechnik[Grad-verleihende Institution]
	10085032-7

Zusammenfassung:

Underwater imaging has been widely used as a tool in many fields, however, a major issue is the quality of the resulting images/videos. Due to the light's interaction with water and its constituents, the acquired underwater images/videos often suffer from a significant amount of scatter (blur, haze) and noise. In the light of these issues, this thesis considers problems of low-resolution, blurred and noisy underwater images and proposes several approaches to improve the quality of such images/video frames. Quantitative and qualitative experiments validate the success of proposed algorithms. [Englisch]

Dokumenttyp:

Dissertation

Einrichtung:

Fakultät für Informatik und Elektrotechnik

Sprache:

Englisch

Sachgruppe der DNB:

000 Allgemeines, Wissenschaft

004 Informatik

Veröffentlichung /
Entstehung:

Rostock

Rostock: Universität Rostock