Presentation 2017-03-02
A New Hough Transform Detecting Thick Line by Analysis of Vote Distribution
Kazuo Ohzeki, Takuya Okunuki, Yoshikazu Kido, Yutaka Hirakawa, Simon Geiger, Stefan Schneider,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Hough transform is able to detect thin lines well, but could not detect thick lines with keeping directions of the lines. In this paper, we first detect flatness of the distribution of Hough transformed data. Peak of Hough transformed data indicates the longest line, but does not indicate longer segment of a rectangle. The flatness is the key feature to detect longer segment of a rectangle. The experiments show good performance in detecting correct directions for white lanes of road images and detecting correct angles for office documents with slanted characters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hough transform / Thick line / Diagonal Line / Distribution / Vote
Paper # LOIS2016-81
Date of Issue 2017-02-23 (LOIS)

Conference Information
Committee LOIS
Conference Date 2017/3/2(2days)
Place (in Japanese) (See Japanese page)
Place (in English) N.Ohama Memorial Hall
Topics (in Japanese) (See Japanese page)
Topics (in English) Nobumoto Ohama Memorial Hall
Chair Hiroyuki Nishi(Sojo Univ.)
Vice Chair Tomohiro Yamada(NTT)
Secretary Tomohiro Yamada(NTT)
Assistant Yukihiro Nakamura(NTT)

Paper Information
Registration To Technical Committee on Life Intelligence and Office Information Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A New Hough Transform Detecting Thick Line by Analysis of Vote Distribution
Sub Title (in English) Using Only Hough Space Without Refferring the Original Space
Keyword(1) Hough transform
Keyword(2) Thick line
Keyword(3) Diagonal Line
Keyword(4) Distribution
Keyword(5) Vote
Keyword(6)
1st Author's Name Kazuo Ohzeki
1st Author's Affiliation Shibaura Institute of Technology(SIT)
2nd Author's Name Takuya Okunuki
2nd Author's Affiliation Shibaura Institute of Technology(SIT)
3rd Author's Name Yoshikazu Kido
3rd Author's Affiliation Shibaura Institute of Technology(SIT)
4th Author's Name Yutaka Hirakawa
4th Author's Affiliation Shibaura Institute of Technology(SIT)
5th Author's Name Simon Geiger
5th Author's Affiliation University of Applied Sciences Kempten(UAS)
6th Author's Name Stefan Schneider
6th Author's Affiliation University of Applied Sciences Kempten(UAS)
Date 2017-03-02
Paper # LOIS2016-81
Volume (vol) vol.116
Number (no) LOIS-488
Page pp.pp.105-110(LOIS),
#Pages 6
Date of Issue 2017-02-23 (LOIS)