Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Non-reference stereo image quality evaluation method based on local-to-global feature regression

A local regression, stereo image technology, applied in the field of image processing, can solve problems such as binocular competition and binocular masking

Active Publication Date: 2019-08-09
TIANJIN UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Considering the phenomenon of binocular competition and binocular masking when human eyes watch stereoscopic images, the method of simply evaluating the quality of left and right viewpoint images has certain defects.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-reference stereo image quality evaluation method based on local-to-global feature regression
  • Non-reference stereo image quality evaluation method based on local-to-global feature regression
  • Non-reference stereo image quality evaluation method based on local-to-global feature regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention first assigns different labels to the image blocks of the left and right viewpoints through the feature similarity (FSIM) algorithm, uses the calculated labels to guide the local regression neural network of the left and right channels to perform pre-training at the same time, and uses the trained local regression neural network The parameters are saved. Then, the local regression neural network of the left and right channels is fused, and on the basis of the pre-training model, the subjective evaluation value (DMOS) is used as the label to guide the global regression neural network to train, and the parameters of the global regression neural network are fine-tuned. Implement global regression of features. The quality of the stereoscopic image is extracted and predicted by the trained global regression neural network.

[0022] Local RNN label generation:

[0023] The content of this work is partly based on the algorithm proposed in literature [9]...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the field of image processing, and aims to establish an efficient non-reference stereo image quality evaluation method based on local-to-global feature regression. The stereoimage quality evaluation method is more accurate in quality prediction, does not need to depend on an original reference image, can replace a subjective evaluation result to a certain extent, improvesthe efficiency of stereo image quality evaluation work, and provides certain convenience for subsequent work. Therefore, the technical scheme adopted by the invention is as follows: the non-referencestereo image quality evaluation method based on local-to-global feature regression comprises the following steps: firstly, respectively endowing image blocks of a left viewpoint and a right viewpointwith different tags through a feature similarity FSIM algorithm, guiding a local regression neural network comprising a left channel and a right channel to perform pre-training by utilizing the calculated tags, and storing parameters of the trained local regression neural network. The method is mainly applied to image processing occasions.

Description

technical field [0001] The invention belongs to the field of image processing and relates to the application of deep learning in quality evaluation of stereoscopic images. Specifically, it relates to a no-reference stereo image quality assessment method based on local-to-global feature regression. Background technique [0002] In recent years, with the continuous development of 3D technology, more and more attention has been paid to the research on stereo images. Since the stereoscopic image may be distorted during the transmission process, the quality of the stereoscopic image will be affected, and the result will directly reflect people's visual perception of the stereoscopic image. Therefore, how to effectively evaluate the quality of stereoscopic images has become one of the key issues in the field of stereoscopic image processing and computer vision. Based on this current situation, the present invention proposes a no-reference stereoscopic image quality evaluation me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/00G06N3/04
CPCG06T7/0002G06T2207/30168G06N3/045
Inventor 李素梅韩永甜薛建伟
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products