No-reference quality evaluation method of compression perception recovery images
A technology for image restoration and compressed sensing, applied in image enhancement, image analysis, image data processing, etc., and can solve problems such as poor performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] The present invention will be described in detail below in conjunction with the accompanying drawings.
[0022] Such as figure 2 and image 3 as shown, image 3 There is obvious distortion. According to the distortion characteristics in the image, the features of the image are extracted. Furthermore, a model is trained with SVR through a collection of features. Through this model, the quality score of the image is predicted.
[0023] Such as figure 1 As shown, Step 1: The experiment is carried out in the 'compressed sensing restored image database'. A total of 300 images (512*512) in the database are restored images obtained by 10 compressed sensing restoration algorithms and 3 different compression degrees. They contain distortions of different kinds and degrees. Using the fuzzy evaluation algorithm LPC-SI, calculate the sharpness feature value X=(x ij ) M*N . Taking the average value of all elements in the sharpness feature value, that is Where i = 1, 2...
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