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

Anaglyph coding method based on three-dimensional self-organizing mapping

A technology of self-organizing mapping and parallax image, applied in the field of image processing, can solve problems such as nonlinear mapping of difficult 3D signals

Inactive Publication Date: 2014-04-30
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is difficult to effectively realize the nonlinear mapping of 3D signals by directly using the traditional SOM algorithm

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
  • Anaglyph coding method based on three-dimensional self-organizing mapping
  • Anaglyph coding method based on three-dimensional self-organizing mapping
  • Anaglyph coding method based on three-dimensional self-organizing mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0092] This embodiment presents the results of various algorithms.

[0093] (1) 3D SOM initialization algorithm

[0094] ① Variance-based initialization algorithm

[0095] Table 1 Comparison of initialization algorithms with and without variance

[0096]

[0097] The variance sorting method is adopted, and the allocation ratio of high frequency and low frequency is changed by setting the codebook threshold to achieve the purpose of affecting the performance of the algorithm.

[0098] Table 2 The influence of threshold on the performance of 3D SOM algorithm for variance classification

[0099]

[0100] ② Codebook size and 3D topology

[0101] The three-dimensional neighborhood SOM algorithm designs codebooks with N of 1568, 784 and 392, and each N value corresponds to a different three-dimensional topology of the codebook.

[0102]Table 3 Comparison of various arrangement structures when the codebook size is 1568

[0103]

[0104] Table 4 Comparison of various arr...

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 provides an anaglyph coding method based on three-dimensional self-organizing mapping. The method comprises the steps that a three-dimensional SOM network structure for processing a three-dimensional image is established, a three-dimensional SOM algorithm is utilized to code an anaglyph, and a three-dimensional image compressing code is obtained. The method comprises an initializing algorithm, a competition algorithm, a neighbourhood algorithm and a learning algorithm. The method achieve mapping from two dimensions to three dimensions, a designed code book has good performance in the aspect of the peak signal to the noise ratio of a three-dimensional reconstruction image, three-dimensional image coding is achieved, and a right image reconstructed by decoding the anaglyph and a left image has good subjective and objective evaluation. The anaglyph coding method has important principle and engineering practical significance and wide application prospects and can be widely applied to three-dimensional image processing, remote sensing image processing, medical image processing, target identification, three-dimensional video coding and the like.

Description

technical field [0001] The invention relates to image processing, in particular to the processing of three-dimensional stereoscopic images, and more specifically to a parallax image coding method based on three-dimensional self-organizing maps. Background technique [0002] Finn T.Kohonen proposed Self-Organizing Map (SOM), or Self-Organizing Feature Map in 1982. It is an unsupervised trained neural network that automatically clusters input patterns by training itself. SOM is a two-layer structure network with lateral association ability. The output nodes are distributed in a two-dimensional array. Each input node and output node are connected with variable weights. Each output node has a topological neighborhood. Neighborhoods change over time. When the neural network is used in codebook design, the vector dimension is used as the number of input nodes of the neural network, the size of the codebook is used as the number of output nodes, and the variable weight between th...

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
Patent Type & Authority Applications(China)
IPC IPC(8): H04N19/597H04N19/149H04N19/154H04N13/00
Inventor 黎洪松王艳华
Owner GUILIN UNIV OF ELECTRONIC TECH
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

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