Presentation 2009-01-23
Illumination artifact removal using bidimensional empirical mode decomposition
Takeshi OYA, Toshihisa TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Images commonly contain some illumination artifacts. When we apply object recognition algorithms for those images, the performance may decrease. To remove the illumination artifact, methods that use empirical mode decomposition (EMD) have been introduced. The EMD provides an adaptive decomposition that decomposes a signal into the so-called intrinsic mode functions (IMFs) and the residue. The residue can be regarded as a component representing the illumination artifact to be removed. However, these methods can lose shades of objects in the original image. In this paper, we propose a method that does not discard the residue but rescale the residue. Experimental results support the analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) empirical mode decomposition / intensity transformation / object recognition
Paper # SIP2008-161,RCS2008-209
Date of Issue

Conference Information
Committee RCS
Conference Date 2009/1/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Radio Communication Systems (RCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Illumination artifact removal using bidimensional empirical mode decomposition
Sub Title (in English)
Keyword(1) empirical mode decomposition
Keyword(2) intensity transformation
Keyword(3) object recognition
1st Author's Name Takeshi OYA
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology()
2nd Author's Name Toshihisa TANAKA
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
Date 2009-01-23
Paper # SIP2008-161,RCS2008-209
Volume (vol) vol.108
Number (no) 391
Page pp.pp.-
#Pages 6
Date of Issue