Super-resolution reconstructed image quality Contourlet domain evaluation method

Abstract

A super-resolution reconstructed image quality Contourlet domain evaluation method comprises the steps of respectively performing non-downsampling Contourlet transformation on an original low-resolution image and a super-resolution reconstructed image to obtain directional sub-band coefficient images of a transformation domain; utilizing directional entropy to calculate sub-band image energy distribution, evaluating the increase degree of detail information of the super-resolution reconstructed image with energy distribution change degree as the standard, wherein the increase degree of the detail information of the super-resolution reconstructed image is marked as a reconstruction entropy factor; dividing pixels in the reconstructed image into strong edge pixels, weak edge pixels and noise pixels according to characteristics of the Contourlet coefficients, evaluating the severity degree of the ringing effect, for the strong edge pixels, according to the coefficient change in neighborhood domains of front and rear edge pixels to obtain a ringing factor, and evaluating the fuzzy degree of the weak edge pixels to obtain a fuzzy factor; fusing the entropy factor, the ringing factor and the fuzzy factor to obtain the unified quality evaluation standard.

Description

technical field [0001] The invention relates to a Contourlet domain evaluation method for super-resolution reconstructed image quality, belonging to the technical field of digital image processing. Background technique [0002] The noise introduced by down-sampling in image digital acquisition, transformation and quantization during compression, and the influence of various factors such as relative motion and atmospheric disturbance in image conversion or transmission will cause image degradation, which greatly affects the image quality. The utility of data. Super-resolution reconstruction technology uses image processing methods to estimate a high-resolution image from a single or multiple blurred, noisy, and spectrally aliased low-resolution degraded images, without modifying the hardware structure of the imaging system. effective means to solve this problem. The quality of reconstructed images is a key indicator to evaluate the performance of super-resolution methods. F...

AI Technical Summary

Problems solved by technology

Among them, the evaluation based on structural similarity is the most widely used. It uses the characteristics of human high-level vision to be sensitive to image structure, and measures the visual difference between the distorted image and the original image from the similarity of brightness, contrast, and structure. However, the human visual system The processing of the image structure is extremely complicated, and the structural similarity only describes a certain aspect of the human visual system, and its evaluation index has a strong correlation with the image distortion type and the content of the image itself, so it is often quite different from the subjective evaluation.

Images