A non-reference image quality objective evaluation method based on Bayesian compressed perception

Abstract

The invention discloses a non-reference image quality objective evaluation method based on Bayesian compression perception. In this method, the reconstructed image is reconstructed from the input distorted image by using the reconfigurable property of Bayesian compressed sensing method, the structure similarity index of the input distorted image and the reconstructed image is calculated, and the average value of the structure similarity index of the whole image is extracted as the similarity feature of image quality evaluation. The input distorted image is normalized, the uniform local binarypattern histogram of the normalized image is extracted as the uniform local binary pattern feature, and according to the similarity feature extracted from Bayesian compressed perception and the uniform local binary mode histogram feature, the image quality evaluation feature is obtained. The image quality evaluation feature is sent to the support vector regression machine for training and testing,and the image quality evaluation result of the input distorted image is obtained. This method utilizes the reconfigurable property of Bayesian compressed sensing method to evaluate the image quality,and improves the precision of image quality evaluation.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to an image quality evaluation method, in particular to a no-reference image quality evaluation method based on Bayesian compressed sensing. Background technique [0002] Image quality evaluation is a key issue in the field of image processing. Image quality evaluation methods can be divided into subjective image quality evaluation methods and objective image quality evaluation methods according to whether people participate. Subjective image quality evaluation methods are scored by humans, and the evaluation results are accurate, but the evaluation process is complex, time-consuming, and difficult to be applied in real time. The objective image quality evaluation method does not require human participation, and the image quality is automatically predicted by a specific computer algorithm. According to whether the original undistorted image is used as a reference, objective image qual...

AI Technical Summary

Problems solved by technology

Since the method for a specific type of distortion needs to know its type of distortion, its scope of application is limited, so research on general methods applicable to multiple types of distortion has become a hot spot in the field of image quality evaluation.

However, at this stage, the understanding of the human visual system and the statistical characteristics of natural images is not sufficient, and the research progress of non-reference image quality evaluation is relatively slow.

Images