Image restoration method in strong scattering environment based on NSCT image fusion

Abstract

The invention discloses a polarization imaging degraded image restoration method in a strong scattering environment based on NSCT image fusion, and belongs to the field of optical image processing. The method comprises: underwater image preprocessing, algorithm input, NSCT decomposition, orthogonal matching pursuit (OMP) reconstruction, coverage of the edge of a source image on an initial fusion image by an edge detection technology, and algorithm output. Information entropy (EN), average gradient (AG) and standard deviation (STD) are selected as image evaluation indexes, and, through compared with the algorithm of the invention, image restoration is performed by using a Wiener filtering method, a constrained least square filtering method and a blind deconvolution method. According to experimental calculation, the algorithm provided by the invention is the highest in the aspects of information entropy (EN), average gradient (AG) and standard deviation (STD), that is, the algorithm is most effective, and the average gradient (AG) is improved by 3.5 times compared with intensity imaging and is improved by 10% compared with polarization imaging; and the standard deviation (STD) is improved by 44% compared with intensity imaging, and is improved by 17% compared with polarization imaging.

Description

technical field [0001] The invention belongs to the field of optical image processing, and in particular relates to a method for restoring a degraded image of polarization imaging in a strong scattering environment based on NSCT image fusion. Background technique [0002] The ocean area accounts for about 70% of the earth, and the ocean has a lot of resources that can be exploited and utilized by human beings. With the over-exploitation of land resources by humans, the problem of ecological imbalance has become more and more serious, so humans have shifted their attention to the development of underwater resources. However, due to the complex and changeable underwater environment, it is not easy to develop underwater resources. Therefore, underwater polarization imaging technology and detection technology have become the focus of attention, and have been widely used in the development and exploration of underwater resources, military reconnaissance and so on. [0003] When...

AI Technical Summary

Problems solved by technology

Contourlet transform can effectively describe the contour information of the image, but it has translation invariance, which will cause image distortion in image processing.

Based on the dark channel, image fusion and Retinex algorithm, although these can improve the underwater imaging quality to a certain extent, the color, details and clarity of the image still need to be further improved

Images