Contrast distortion image quality evaluation method based on image entropy

A distorted image and quality evaluation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of contrast distortion, image distortion and degradation, poor performance, quality distortion and degradation, etc., and achieve a good evaluation effect

CN112446879AActive Publication Date: 2021-03-05TIANJIN UNIV OF SCI & TECH
12 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-03-05

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a contrast distortion image quality evaluation method based on image entropy, and belongs to the technical field of image processing. According to the method, the quality of a contrast distortion image is evaluated by utilizing the image entropy according to the characteristic change rules of the information amount and a histogram of the contrast distortion image, so that the problem of contrast distortion degradation of the image during transmission, storage, compression and the like of the image is solved. Meanwhile, the defect of lack of contrast distortion evaluationmethods in the field of image quality evaluation is overcome, and the accuracy and effectiveness of the method are obviously improved compared with those of existing similar evaluation methods. The obtained image distortion evaluation data can objectively describe and evaluate the contrast distortion degradation degree of the image; the evaluation result conforms to human eye perception, and themethod has good evaluation performance, can be used in the image processing fields of image fusion, image enhancement, image recognition and the like, and has good application potential and values.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of image evaluation and image processing, in particular to a contrast distortion image quality evaluation method based on image entropy. Background technique

[0002] In the past ten years, it is a period of vigorous development of image quality evaluation. Since the visual quality of image perception is crucial to the design and optimization of image and video processing systems, image quality assessment (IQA) has always been a hot research topic in related fields. Usually, the images presented to people are processed through different process stages such as acquisition, compression, and transmission. Various image distortions generated by these processes, including compression artifacts, blur, noise, etc., will seriously affect the vision of the image. perceived effect. In the process of image acquisition, compression, transmission, etc., unfavorable lighting conditions during image capture and transmiss...

Examples

Embodiment 1

[0034]This embodiment selects a standard image in the CSIQ (Categorical subjective image quality) database and two corresponding overall contrast reduction distorted images with different degrees of distortion as the input of the present invention to perform the contrast distortion image quality described in the present invention. Description of the evaluation method; the CSIQ database contains 30 standard images and 866 distorted images, and the distortion types of the distorted images include JPEG compression, JPEG2000 compression, overall contrast reduction, additive Gaussian pink noise, additive Gaussian White noise and Gaussian blur; the CSIQ database provides the average human perception error value (DMOS) of the distorted image, and the value range of DMOS is [0,1]. The larger the DMOS, the lower the image quality, and the human perception the worse the effect.

[0035] image 3 It is the selected standard image, the file name is src_imgs1600; Figure 4 Downscaling th...

Embodiment 2

[0039] This embodiment selects 30 standard images with different contents and 146 overall contrast reduction distortion images from the CSIQ database (each standard image corresponds to 3 or 4 distorted images with different degrees of contrast distortion, and the distorted images are obtained by performing different degrees of distorted images on standard images. The image obtained by the contrast distortion processing, the contrast of the image has been distorted and changed on the whole of the image) as the input of the present invention, the calculation of the contrast distortion image quality evaluation method of the present invention is carried out; the evaluation method of the present invention obtained The evaluation data is consistent with the DMOS data of the CSIQ database image and the image characteristics perceived by the human eye.

[0040] Combining the above-mentioned standard image and the corresponding overall contrast reduction distortion image, using the tec...

Embodiment 3

[0045] In this embodiment, a color image captured by a digital device is selected, and then the color image is subjected to partial area contrast reduction and distortion processing to obtain a standard image img0, a distorted image img1, a distorted image img2, and a distorted image img3 respectively.

[0046] Then, use img0 as the standard image I of the present invention ref , img1 as the distorted image I of the present invention dis ; Reuse the technical scheme of the present invention, Figure 1-2 The image entropy H described in operation 2 of the flow process shown and the technical solution of the present invention I =αH R +βH G +γH B , α=β=γ=1 / 3, calculate the distortion evaluation data S1 of the distorted image img1; use img0 as the standard image I of the present invention ref , img2 as the distorted image I of the present invention dis ; Reuse the technical scheme of the present invention, Figure 1-2 The image entropy H described in operation 2 of the flow...