Stereoscopic image non-reference quality evaluation method based on visual perception characteristics

Abstract

The invention relates to a stereoscopic image non-reference quality evaluation method based on visual perception characteristics. The method includes the steps that firstly, a region in which the human eyes are interested in an image is selected through a visual prominence model algorithm; secondly, a depth map for representing stereoscopic visual information is extracted from the region of interest as an evaluation basis through a left view and a right view; thirdly, characteristic statistical treatment is conduced on the depth value of the region, and the influence of human eye depth sensitive characteristics on depth perception is considered in the process; eventually the video sequence depth quality value is calculated by the combination of characteristic information of time domains. Compared with a traditional method, the stereoscopic image non-reference quality evaluation method has the advantages that result accuracy is greatly improved, high generating efficiency of the depth map is possessed, weight factors for representing that the depth level affects human eye depth sensitivity are added in a stereoscopic feeling quality evaluation model, and then stereoscopic image quality is more accurately evaluated.

Description

technical field [0001] The invention relates to a no-reference quality evaluation method for stereoscopic images based on visual perception characteristics. Background technique [0002] Stereoscopic image depth perception quality evaluation refers to a method for evaluating the stereoscopic experience quality of stereoscopic image content. There are two methods for evaluating stereoscopic image quality: subjective evaluation and objective evaluation. subjective evaluation method [1] Although the result of the method is more accurate, it needs to organize specialized personnel to observe, which is expensive and time-consuming, and is not suitable for real-time applications and system integration. Therefore, objective quality assessment methods [2, 3] It has become a hot topic in recent years. [0003] In the objective evaluation method of stereoscopic images, in 2008, Benoit expanded the traditional 2D image objective quality evaluation method, introduced the disparity ma...

AI Technical Summary

Problems solved by technology

This step estimates the disparity information of the left and right views, and then converts it into the corresponding depth value. However, the disparity estimation needs to match the positions of the corresponding pixels in the left and right images, and the calculation complexity is very high, resulting in low evaluation efficiency. Great impact on depth perception [8] , while the saliency model can calculate the degree of human eye attention of the image, we use the graph-based visual attention model [8] Obtain the attention graph, the model constructs the relationship between nodes through the Markov chain, the calculation is simple and the performance is excellent

Images