Image display adaptation quality evaluation method based on visible distortion pooling

Abstract

The invention relates to an image display adaptive quality evaluation method based on visible distortion pooling. The method comprises the following steps of S1, reading an original image, and generating a saliency map S by using a saliency object detection algorithm; S2, establishing a pixel-level mapping relation between the original image and the display adaptive image by using an image registration method; S3, calculating the block-level fidelity F of the image by using the pixel-level mapping relation; and S4, pooling the saliency map S and the image fidelity F by using a visible distortion pooling strategy, and calculating the overall objective evaluation quality Q of the display adaptive image. According to the invention, a human eye evaluation mechanism in image objective quality evaluation can be effectively simulated and displayed; the defect of an importance weighting pooling strategy during inter-group comparison is overcome, the consistency between an evaluation score anda subjective score of an objective evaluation method can be improved, and the method can be applied to the objective quality evaluation field of displaying adaptive images and other application fieldsneeding to adopt the pooling strategy to be combined with local information to evaluate the overall quality.

Description

technical field [0001] The invention relates to the fields of image and video processing and computer vision, in particular to an image display adaptive quality evaluation method based on visible distortion pooling. Background technique [0002] In recent years, researchers have proposed many image display adaptation methods to manipulate the content of images to adapt to various target display screens with different sizes and aspect ratios. However, there is still no image display adaptation method that can be well adapted to various application scenarios and produce satisfactory display adaptation images. There are many factors restricting the further development of image display adaptation methods, one of which is that there is still a lack of image display adaptation quality assessment (IRQA) methods that are more consistent with human subjective perception. Most image display adaptation methods often use small-scale subjective tests on the dataset to verify the effecti...

AI Technical Summary

Problems solved by technology

However, the current similarity measure for measuring local quality is still insufficient, and the commonly used Importance Weighted Pooling (IWP) strategy is also prone to the problem of changing the rules of importance when comparing between groups, so the consistency between objective evaluation results and subjective scores still not high

Images