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

Multi-focus image fusion method in stationary surfacelet domain based on composite pcnn

A multi-focus image and fusion method technology, applied in the field of multi-focus image fusion in the smooth Surfacelet domain, to achieve good fusion effect, scattered gray level distribution, and outstanding details

Active Publication Date: 2016-12-21
INNER MONGOLIA UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention overcomes the defects of the traditional multi-focus image fusion method and improves the fusion effect

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
  • Multi-focus image fusion method in stationary surfacelet domain based on composite pcnn
  • Multi-focus image fusion method in stationary surfacelet domain based on composite pcnn

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as figure 1 As shown, this embodiment includes the following steps:

[0030] The first step: the registered left focus original image And right to focus the original image Perform Surfacelet transformation respectively to obtain the directional subband coefficients of the Surfacelet domain;

[0031] In the Surfacelet transformation, the original image is decomposed into two layers to obtain low-frequency coefficients and high-frequency coefficients, namely, low-frequency coefficients with And high frequency coefficient with , Where: the first layer has 4 directional sub-bands, and the second layer has 4 directional sub-bands, where: k is the number of layers of scale decomposition, and l is the number of directions of directional decomposition.

[0032] Step 2: After initializing the parameters of the compound neural network PCNN, the low-frequency coefficients with Using dual-channel PCNN for fusion, high-frequency coefficients with Use PCNN-based fusion to obta...

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 discloses a multi-focus image fusion method in a stable Surfacelet domain based on a compound PCNN. Firstly, two registered multi-focus source images are decomposed by Surfacelet transformation to obtain low-frequency coefficients and high-frequency coefficients, and all coefficients are input Composite PCNN, the low-frequency coefficients are selected by the dual-channel PCNN part of the composite PCNN, and the high-frequency coefficients are selected by the PCNN part; finally, the fusion image is obtained through Surfacelet inverse transformation. The invention overcomes the defects of the traditional multi-focus image fusion method and improves the fusion effect.

Description

Technical field [0001] The invention relates to a smooth Surfacelet domain multi-focus image fusion method based on a composite PCNN, which belongs to the technical field of image processing. Background technique [0002] The limited viewing characteristics of different types of optical devices cause them to focus differently on multiple objects with different depths in the same target area. These images represent the same scene with different emphasis, so there are complementary information. [0003] Multi-focus image fusion can make multiple target objects at different distances appear clearly at the same time, which lays a good foundation for feature extraction and image recognition. [0004] Multi-focus image fusion methods include image fusion based on spatial domain and image fusion based on transform domain. At present, methods based on transform domain are the main ones. Commonly used transform domain fusion methods include wavelet transform and multi-scale geometric analysi...

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 Patents(China)
IPC IPC(8): H04N5/262G06T5/50
Inventor 张宝华吕晓琪张传亭
Owner INNER MONGOLIA UNIV OF SCI & 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