Presentation 2001/1/18
Detection of the gastric region by the line tracking in the object space
Y. Yoshinaga, S Fukushima, H. Kobatake,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new method to detect the gastric region by extracting of long and continuous curves. The border of the gastric region consists of two different types of lines. One is the line convex region, a tangential shadow of the gastric wall onto the image plane;the other is the edge of the barium pool. We treat both types of lines equivalently by applying the rotated differential filter and the line-convergence vector field model. Furthermore, we introduce a new tracking method to understanding curves constructed from line-objects. This method called the line-object-based tracking method enables easy and stabile understanding of each line structure within an image. The effectiveness of the method is shown by comparing the experimental results with the sketch by a radiologist.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Double contrast X-ray image / Line-convergence vector field model / Line-object tracking
Paper # MI2000-59
Date of Issue

Conference Information
Committee MI
Conference Date 2001/1/18(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 Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detection of the gastric region by the line tracking in the object space
Sub Title (in English)
Keyword(1) Double contrast X-ray image
Keyword(2) Line-convergence vector field model
Keyword(3) Line-object tracking
1st Author's Name Y. Yoshinaga
1st Author's Affiliation Graduate School, Kyushu Institute of Design()
2nd Author's Name S Fukushima
2nd Author's Affiliation Graduate School, Kyushu Institute of Design
3rd Author's Name H. Kobatake
3rd Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo Univ.of Agri.and Tech.
Date 2001/1/18
Paper # MI2000-59
Volume (vol) vol.100
Number (no) 596
Page pp.pp.-
#Pages 6
Date of Issue