Pattern Selective Image Fusion for Multi-focus Image Reconstruction

This paper presents a method for fusing multiple images of a static scene and shows how to apply the proposed method to extend depth of field. Pattern selective image fusion provides a mechanism for combining multiple monochromatic images through identifying salient features in the source images and...

Full description

Saved in:
Bibliographic Details
Published inComputer Analysis of Images and Patterns pp. 677 - 684
Main Authors Maik, Vivek, Shin, Jeongho, Paik, Joonki
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2005
Springer
SeriesLecture Notes in Computer Science
Subjects
Applied sciences
Artificial intelligence
Automatic Gain Control
Computer science; control theory; systems
Discrete Cosine Transformation
Exact sciences and technology
Image Fusion
Pattern recognition. Digital image processing. Computational geometry
Saliency Function
Source Image
Image analysis
Consumer
Image processing
Filter
Video cameras
Data fusion
Pattern analysis
Laplacian
Monochromatic
Depth of field
Image reconstruction
Multiple image
Online AccessGet full text

Cover

More Information
Summary:This paper presents a method for fusing multiple images of a static scene and shows how to apply the proposed method to extend depth of field. Pattern selective image fusion provides a mechanism for combining multiple monochromatic images through identifying salient features in the source images and combining those features in to a single fused image. The source images are first decomposed using filter subtract decimate (FSD) in laplacian domain. Thesum-modified-Laplacian (SML) is used for obtaining the depth of focus in the source images. The selected images are then blended together using monotonically decreasing soft decision blending (SDB), which enables smooth transitions across region boundaries. The resulting fused image utilizes focus information that is greater than that of the constituent images, while retaining a natural verisimilitude. Experimental results show the performance of the depth of focus extension using consumer video camera outputs.
Bibliography:This work was supported by Korean Ministry of Science and Technology under the National Research Laboratory Project and by Korean Ministry of Information and Communication under the Chung-Ang University HNRC-ITRC program.
ISBN:9783540289692
3540289690
ISSN:0302-9743
1611-3349
DOI:10.1007/11556121_83