Tone-mapped image quality evaluation method based on exposure analysis

Abstract

The invention discloses a tone-mapped image quality evaluation method based on exposure analysis. The method comprises the following steps: exploring exposure properties of each area in a high dynamic range image by adopting a pre-exposure mode, dividing the high dynamic range image into an area that is easy to cause overexposure, an area that is easy to cause underexposure, and an area that is easy to have normal exposure, and extracting different quality features in different areas to ensure that the subsequent quality feature extraction can be more targeted. According to the tone-mapped image quality evaluation method, in consideration of the difference of distortion forms in a tone-mapped image and a traditional image, image features such as the exposure exception rate, underexposure residual energy, overexposure residual energy and exposure color indexes are extracted in the tone-mapped image based on exposure area segmentation, and thus the quality reduction degree of the tone-mapped image can be reflected more accurately; and the correlation between the obtained objective evaluation results and the subjective perception of human eyes can be effectively improved from two aspects of exposure area segmentation and quality feature extraction.

Description

technical field [0001] The invention relates to an image quality evaluation technology, in particular to a color scale mapping image quality evaluation method based on exposure analysis. Background technique [0002] With the rapid development of image acquisition and imaging technology, high dynamic range imaging technology has received more and more attention because it can display richer image scene information, and has gradually become the research focus in the field of imaging display. However, traditional low dynamic range display devices are commonly used in various image processing systems at this stage. Therefore, in practical applications, it is necessary to use color scale mapping operators to process high dynamic range images, so as to make them backward compatible with Conventional low dynamic range display devices. Due to the non-linear mapping relationship of the color scale mapping operator, the quality of the color scale mapping image generated after its pr...

AI Technical Summary

Problems solved by technology

However, there is a large difference between the distortion phenomena that degrade the image quality of level mapping and the types of distortion faced in traditional image quality assessment

Therefore, methods such as feature extraction with better performance in traditional image quality evaluation cannot accurately describe the distortion in the level map image, so the subjective consistency of existing methods still needs to be improved

Images