Respiratory effect measuring method and system

Abstract

The invention provides a respiratory effect measurement method and system, and relates to the technical field of image quality testing, and the method comprises the steps: collecting a video, carryingout the scene classification of the video according to the image complexity, and obtaining a plurality of test scenes; obtaining an image of each test scene, and calculating definition information ofthe image by adopting a definition algorithm; evaluating the respiratory effect of the test scene according to the definition information to obtain a respiratory effect evaluation value; and carryingout weighted calculation on the respiratory effect evaluation values corresponding to the plurality of test scenes according to a preset weight to obtain a respiratory effect comprehensive evaluationvalue. According to the method, objective evaluation of the respiratory effect can be realized, and the accuracy, repeatability and economy of the respiratory effect test are improved.

Description

technical field [0001] The invention relates to the technical field of image quality testing, in particular to a method and system for measuring breathing effects. Background technique [0002] The objectification of image quality testing has always been one of the important propositions of camera function testing. Breathing effect, as an image feature introduced by the encoding algorithm, has an important impact on the stability of image performance, and has been concerned by customers for a long time. Most of the previous evaluations were highly subjective evaluations, such as obvious / not obvious, serious / not serious, subject to the subjective impressions of different testers, and the test results cannot be compared longitudinally between different test samples over time, so the evaluation is inaccurate And time-consuming and laborious. It is increasingly urgent to develop an objective test method that can be used to test the breathing effect. [0003] At present, the m...

AI Technical Summary

Problems solved by technology

However, the subjective comparison test method is simple and rough, subject to the subjective judgment of different individuals, the accuracy of the test results is average; and the single test result cannot be effectively compared with subsequent tests, there are a lot of repeated tests, the efficiency is low, time-consuming and laborious

Incorporating noise, sharpness and other image test indicators into the comprehensive evaluation method, the test directly depends on other test indicators, and cannot directly feed back the phenomenon characteristics of the breathing phenomenon itself, and the results will inevitably have deviations; it is also impossible to avoid the fundamental problem that the test cannot be used. If it is necessary to compare multiple samples in different time intervals, in order to make the results referable, repeated tests have to be carried out

PSNR evaluation method, PSNR tends to deal with image differences before and after processing, and the I frame and P frame that need to be compared for breathing effect belong to different GOP (Group of Picture, picture group), there is no corresponding relationship between the two before and after processing, so If you follow this line of thought to continue this evaluation, you can directly compare the difference between frames without forcing the use of PSNR; a large number of long-term feedback at home and abroad shows that when using PSNR to test different types of image evaluation, its test value and human perception value There are large errors, and it is impossible to accurately represent the corresponding relationship between the breathing phenomenon and the actual subjective feeling.

Images