SOME STUDIES ON UNDERWATER IMAGE ENHANCEMENT

Abstract

Oceans covers 70% of the earth and are required to be explored for various scientific studies like setting up underwater pipelines, knowing the ecological balance by taking population census of various aquatic species etc. To get such information, capturing images is safe and effective solution, but underwater imagery suffers from poor contrast, bluish green color cast, hazy appearance, blurring and noise due to inherent property of water. Enhancement of underwater images is a challenging task as images are captured in different media having varying salinity, turbidity, green matter etc. and captured at varying depth. Thus, there is a need of an adaptive method which works for all type of underwater images. This thesis provides an effective solution to pre-process the underwater images to make them suitable for scientific studies. Under the umbrella of pre-processing, sub-problems like color correction, contrast correction , haze removal have been addressed irrespective of the underwater media and depth at which the images have been captured. The contributions presented in this thesis are outlined below: • We propose an adaptive method for enhancement of underwater images by using fuzzy rules to find the color cast. Since the color correction depends upon the media, some parameters required for controlling the degree of color correction are found using Multi-Objective optimization (MOPSO). Performance measures which are optimized using MOPSO act as proper guiding mechanisms so that the resultant images have few or no artifacts. Various non-reference based performance measures like entropy, histogram spread, UICM have been used to analyze the results. • We propose a local enhancement solution which tackles the artifacts caused by artificial lighting. It performs color and contrast correction in a localized manner. The two versions are then fused using wavelet based fusion with the help of effective weight maps which chooses the required features from the two versions. ii • We proposed a complete solution which addresses the three major issues of underwater images i.e. color cast, poor contrast, haze. Using basic image enhancement and restoration based methods, the proposed method handles the mentioned issues for the images captured at different depths and in media with varying salinity, turbidity.