Please use this identifier to cite or link to this item:
Title: Deepwater vision enhancement
Authors: Dai, Yi Ying
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2015
Abstract: Nowadays, with the development of underwater detecting techniques, the need of more clear vision of underwater images is increasing. However, current approaches to underwater image enhancement depend on standard models of signal-to-noise ratio (SNR), which gives undesirable outcome of improving the quality of underwater images. Thus, novel method which considers both optical characterization and associated signal processing algorithm should be implemented to dramatically increase the sharpness and clarity of underwater image. There exist a lot of image prior model of haze removal in atmosphere, which might be applied to underwater image enhancement as a reference. Also, plenty of digital signal process (DSP) algorithm were discovered and analyzed, but they are not well-used in underwater image enhancement. Therefore, it is credible that a good combination of correct image prior model and appropriate DSP algorithm would be useful to enhance the underwater image quality. In this project, the characteristics of underwater image would be analyzed and a novel method which contains both dark channel prior (DCP) with optical model and improved contrast limit adaptive histogram equalization (CLAHE) algorithm is proposed to greatly enhance the clarity of underwater image. All the works needed to be done in this project can be achieved by Matlab software.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
main article3.26 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 16, 2024


Updated on Jun 16, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.