Presentation 2007-11-30
Contrast Enhancing Image Fusion by Using Bilateral Filters
Yuzuru YOSHITAKE, Kiichi URAHAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method to fuse multiple images into a single image. Proposed method is an extension of a technique for enhancing contrast of single image to multiple images. We first calculate logarithm of pixel values of each component image and smooth them by using the bilateral filter. Smoothed image is a base component and difference between the original image and its base component is a detail component. We compress the base component and add it to detail component. We finally recover pixel values by exponential function to get contrast enhanced images. When adding every detail component, we weigh each component according to their magnitude in order to preserve salient information in each component image. We experiment the proposed method for flash shot, multiple exposure, multiple focus, multiple light photographs and multimodal medical images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image fusion / contrast enhancement / bilateral filter / softmax fusion
Paper # IE2007-101
Date of Issue

Conference Information
Committee IE
Conference Date 2007/11/22(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Contrast Enhancing Image Fusion by Using Bilateral Filters
Sub Title (in English)
Keyword(1) image fusion
Keyword(2) contrast enhancement
Keyword(3) bilateral filter
Keyword(4) softmax fusion
1st Author's Name Yuzuru YOSHITAKE
1st Author's Affiliation Faculty of Design, Kyushu University()
2nd Author's Name Kiichi URAHAMA
2nd Author's Affiliation Faculty of Design, Kyushu University
Date 2007-11-30
Paper # IE2007-101
Volume (vol) vol.107
Number (no) 358
Page pp.pp.-
#Pages 6
Date of Issue