A full-reference multi-exposure fusion image quality assessment method

Abstract

The present invention is a full-reference multi-exposure fusion image quality evaluation method, which fully considers the characteristics of the human visual system and multi-exposure images, and uses the phenomenon that the human eye is sensitive to the contrast and saturation of the fused image, and performs multi-scale decomposition. Based on this, multiple reference images are fused with contrast as the weight value and used as a new reference image, and then compared with the similarity of contrast and saturation of the multi-exposure fusion image to be evaluated, so as to obtain a single-layer quality evaluation value, and then The final score is obtained by weighted fusion of multi-layer quality evaluation values; this method is simple to calculate, fully reflects the subjective perception of human eyes for multi-exposure fusion images, and can better evaluate the quality of multi-exposure fusion images.

Description

technical field [0001] The invention relates to a full-reference multi-exposure fusion image quality evaluation method based on contrast and saturation. Background technique [0002] With the rapid development of computer and network communication technology, people have higher and higher requirements for the quality of digital images. However, due to the limitation of the hardware level of the existing image acquisition equipment, the brightness dynamic range of the natural scene that the camera can capture is far less than the dynamic range of the natural real scene. For example, from the starlight in the night sky to the dazzling sun, the scene brightness changes A dynamic range of about nine orders of magnitude is covered. Therefore, multi-exposure fusion technology came into being. It combines multiple images with different exposure levels into one image with excellent quality, which makes up for the lack of hardware facilities, and has a wide range of application val...

AI Technical Summary

Problems solved by technology

[0009] However, there are certain limitations in the above traditional objective quality assessment methods for fused images: one is that they do not fully consider the visual characteristics of the human eye; Taking into account the factors of different image exposure

At present, there is a lack of methods for quality assessment of multi-exposure fusion images in the field of image processing

Images