Sparse representation-based style migration image quality objective evaluation method

Abstract

The invention discloses a method for objectively evaluating the quality of a style migration image based on sparse representation, and the method comprises the steps: obtaining structure images of different scales corresponding to each content image, and carrying out the dictionary training operation of a set composed of all sub-blocks in all structure images of the same scale through an unsupervised learning mode, constructing a multi-scale content dictionary; obtaining a three-dimensional feature map of a five-layer convolution layer corresponding to each artistic style image, further obtaining a style feature vector of each three-dimensional feature map based on a Grubrum matrix, and carrying out dictionary training operation on a set formed by the style feature vectors of all the three-dimensional feature maps belonging to the same layer in an unsupervised learning mode; constructing a multi-scale style dictionary; during testing, obtaining a content sparse coefficient matrix and a style sparse coefficient matrix according to the multi-scale content dictionary and the multi-scale style dictionary, and further calculating a quality objective evaluation predicted value of the style migration image; the method has the advantage that the correlation between an objective evaluation result and human eye subjective perception can be improved.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a sparse representation-based style transfer image quality objective evaluation method. Background technique [0002] With the rapid development of image editing technology and artistic creative industry, image style transfer technology has received more and more extensive attention and application, and has become a current research hotspot. Image style transfer technology is a technique that applies the style of one style image to another content image while keeping the structure of the content image unchanged. Although current state-of-the-art methods have shown great success in image style transfer, it is difficult for these methods to distinguish their relative advantages, and image quality prediction for style transfer has been a long-standing problem. However, there is currently no effective objective evaluation method for evaluating the quality of style transfer image...

AI Technical Summary

Problems solved by technology

Currently, existing methods focus on limited factors of style transfer quality, but lack fine-grained quality factors, which have certain limitations and cannot effectively match the aesthetic perception of human observers in practice.

Images