Deepwater vision enhancement
Dai, Yi Ying
Date of Issue2015
School of Electrical and Electronic Engineering
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.
DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Final Year Project (FYP)
Nanyang Technological University