Presentation 1999/10/21
A neural network for character recognition using Hough transformation :robust to variation of size and rotation
Fumio TORIGATA, Shigechika KIMURA, Akio SUZUKI, Masafumi YANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a model that recognizes alphabet characters for various size and rotational position. Normalization using Hough transformation is introduced as preprocess. Center of characters is set to center (ρ=0) at Hough plain and size of characters are regulated by normalization of ρ-direction of their Hough images. In order to treat all rotational changes, Hough transformed image of characters are divided at ρ=0 axis and arranged along θ-axis. Normalizations of arbitrary angles is realized by them. According to this, we showed that it could recognize alphabets and handwriting characters by simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) normalization / character recognition / Hough transformation / neural network / backpropagation
Paper # PRMU99-88
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/10/21(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A neural network for character recognition using Hough transformation :robust to variation of size and rotation
Sub Title (in English)
Keyword(1) normalization
Keyword(2) character recognition
Keyword(3) Hough transformation
Keyword(4) neural network
Keyword(5) backpropagation
1st Author's Name Fumio TORIGATA
1st Author's Affiliation Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name Shigechika KIMURA
2nd Author's Affiliation Research Institute of Electrical Communication, Tohoku University
3rd Author's Name Akio SUZUKI
3rd Author's Affiliation Research Institute of Electrical Communication, Tohoku University
4th Author's Name Masafumi YANO
4th Author's Affiliation Research Institute of Electrical Communication, Tohoku University
Date 1999/10/21
Paper # PRMU99-88
Volume (vol) vol.99
Number (no) 380
Page pp.pp.-
#Pages 6
Date of Issue