Contrast distortion image quality evaluation method fusing image entropy and structural similarity characteristics
A technology for image quality evaluation and structural similarity, applied in image analysis, image enhancement, image data processing and other directions, it can solve the problems of poor performance of color image distortion and degradation, image quality distortion and degradation, and achieve good evaluation results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] Select 1 reference image (standard) of the CSIQ (Categorical subjective image quality) database and 2 corresponding overall contrast reduction distorted images with different degrees of distortion, as the input of this embodiment, perform the contrast distortion image quality described in the present invention evaluation of. The CSIQ database contains 30 standard images and 866 distorted images. The distortion types of distorted images include JPEG compression, JPEG2000 compression, overall contrast reduction, additive Gaussian pink noise, additive Gaussian white noise and Gaussian blur. The CSIQ database also provides the average human perception error value (DMOS) of distorted images. The value range of DMOS is [0, 1]. The larger the DMOS, the lower the image quality and the worse the human perception effect.
[0046] image 3 is the selected reference image; Figure 4 It is a contrast distorted image with less distortion, and its DMOS is 0.090; Figure 5 It is a c...
Embodiment 2
[0056] Select 30 different reference images of the CSIQ database and 164 contrast distorted images corresponding thereto as the input of the present invention: 1 reference image and a plurality of distorted images corresponding to it form an input image group, and carry out the method described in the present invention The evaluation calculation of the distorted image quality; The evaluation process of the involved image quality is the same as embodiment one, after inspection, the evaluation data obtained by the evaluation method of the present invention and the DMOS data of the CSIQ database and the visual perception characteristics of the human eye is consistent.
[0057] According to the technical scheme of the present invention and figure 1 and figure 2 As shown in the process, the evaluation data of the above 164 images are acquired. In research, adopt " Pearson's linear correlation coefficient (PLCC) " and " Spearman's order correlation coefficient (SROCC) " index, ev...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com