No-reference image definition detection method

Abstract

The invention relates to a no-reference image definition detection method. The method comprises the following steps of: firstly, calculating a gradient map according to the existing grey-scale map; secondly, positioning strong edge points by using an open edge detection algorithm; thirdly, calculating the edge width of each strong edge point to obtain an edge width cumulative histogram; fourthly, carrying out wavelet transform on the existing gray-scale map, and calculating the energy of high-frequency wavelet coefficient; fifthly, counting a grey-scale histogram according to the existing grey-scale map, and calculating the feature of the grey-scale histogram according to the grey-scale histogram; and finally, estimating the definition of the grey-scale map according to the edge width cumulative histogram, the energy of high-frequency wavelet coefficient and the feature of the grey-scale histogram. According to the method, the definition of images can be detected without reference images, and the definition value is consistent with the subjective feeling of eyes. The method is not influenced by the image content and the luminance of the field of view, and the detection result has a certain robustness to interferences such as coding and noise.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a reference-free image definition detection method. Background technique [0002] In practical applications, images captured by video cameras or cameras are often degraded due to various reasons, resulting in blurred and unclear visual experience of the human eye. Common reasons for image degradation are: compression, sensor performance degradation, electromagnetic interference, out of focus, etc. Image quality includes two aspects: subjective quality and objective quality. Subjective quality refers to the human eye's perception of the overall content and details of the image; objective quality refers to the degree of deviation between the degraded image and the original image. [0003] According to the degree of dependence on the original image, image quality assessment methods are mainly divided into three categories: full-reference, semi-reference and no-reference ima...

AI Technical Summary

Problems solved by technology

[0004] The patent "image processing device, image processing method, program, and storage medium (patent number: 200710137014)" determines the focus state by the sharpness, length and direction of the edge of the object; its disadvantage is that the sharpness estimated by the image with less edge information inconsistent with subjective

The patent "A Method for Measuring Image Sharpness Using Multi-scale Morphological Features (Patent No.: 201110167446)" obtains multi-scale morphological features on the pixel gray value of the image as a measure of sharpness; its disadvantage is that for common Video images with thin stripes or noise interference can easily cause missed detection

The patent "A Method and Device for Image Quality Evaluation (Patent No.: 201010532192)" uses spatial frequency domain characteristic parameters, brightness response nonlinear characteristic parameters, masking effect characteristic parameters, etc. as human visual characteristic parameters, and uses self-learning classification method to train Human visual evaluation model; its disadvantage is that the spatial frequency domain characteristics of the image do not distinguish noise and texture clearl...

Images