Weight Maps Guided Underwater Image Enhancement By Fusion Technique
Saloni Tarhate · Bioscience Biotechnology Research Communications · 2020
The underwater image plays a very important role in today's world in order to explore the unknown underwater world.But the images captured underwater are different from those taken in the air atmosphere.There are lots of problems associated such as haziness, blurriness, non-uniformity, color degradation, etc.All this is due to reflection, refraction, and scattering in water.To overcome these problems enhancement of the underwater image is required to get a better quality image.In this paper, the logarithmic image processing model is proposed as an important part of the methodology for underwater image enhancement.The insight to apply the logarithmic image processing model was taken from the human eye visual concept, as it functions in the logarithmic fashion while the camera functions linearly.A single image approach is used in which a degraded image is taken as an input and then various digital image operations are performed on it to enhance the quality of the underwater image.The insight to apply the logarithmic image processing model was taken from the human eye visual concept, as it functions in the logarithmic fashion while the camera functions linearly.The method is based on the fusion of directly derived images from gamma correction, sharpening, and their associated weight maps.Finally, the fused image is processed through Contrast Limited Adaptive Histogram Equalization (CLAHE) to get the enhanced output.The method is applied on two data set of images, subjective evaluation is computed and results are compared with other methods.To do an objective evaluation, the quality of output image measures through parameters and compared with other available methodologies.The experimental results show that the performance of the proposed method is competitive with that of available methods.