System and method for automatically enhancing underwater images in NSCT (non-subsampled contourlet transform) regions on basis of human visual characteristics

Abstract

The invention provides a system and a method for automatically enhancing underwater images in NSCT (non-subsampled contourlet transform) regions on the basis of human visual characteristics. The system and the method have the advantages that multi-scale and multi-direction edge expression merits and noise removal merits of NSCT are comprehensively utilized, perceptual characteristics of human visual systems are used for reference, accordingly, noise in the NSCT regions can be removed, uneven underwater illumination can be eliminated by the aid of introduced Retinex algorithms, and NSCT contrast mask coefficients on the basis of the human visual characteristics can be generated by the aid of introduced brightness mask and introduced contrast mask characteristics; the NSCT contrast mask coefficients and NSCT low-frequency sub-band coefficients can be respectively automatically regulated by two designed nonlinear mapping functions, accordingly, contrast can be enhanced, and parameters do not need to be manually regulated; the noise can be effectively removed, the contrast of the underwater images can be automatically enhanced, edges of the underwater images can be sharpened, and uneven illumination can be eliminated.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image automatic enhancement method, in particular to an NSCT domain underwater image automatic enhancement system and method based on human visual characteristics. Background technique [0002] In recent years, with the increasing demand for underwater environment perception, underwater imaging technology has developed rapidly and is mainly used in underwater surveys, underwater robots, marine biological monitoring, and military affairs. However, underwater imaging is very different from aerial imaging. Affected by the scattering and attenuation of underwater light, the collected underwater optical images have the characteristics of low contrast, strong noise, uneven illumination and blurred target edges. Manual interpretation and automatic interpretation of images pose great difficulties. Therefore, the study of underwater optical image enhancement technology to impro...

AI Technical Summary

Problems solved by technology

Patent search and the latest search of various scientific and technological documents at home and abroad show that there is no automatic underwater image enhancement method that combines NSCT with human visual characteristics.

Images