Presentation 1995/9/28
Synthesis of Feature Vector for Handwritten Numeral Recognition
Shuji NISHIKAWA, Tetsushi WAKABAYASHI, Fumitaka KIMURA, Yasuji MIYAKE, Toshio TSUTSUMIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Aiming to achieve a recognition accuracy beyond the limit of existing character recognition algorithms, a procedure for synthesizing an efficient feature vector from typical feature vectors is proposed, and the availability is evaluated by recognition experiment. For the purpose, seventeen typical existing feature vectors and seven statistical classifiers were combined and evaluated to select three efficient feature vectors. Then, in order to reduce the dimensionality of the synthesized feature vector, the effect of the dimension reduction on classification accuracy was examined. The best feature vector of size 400 synthesized from the three feature vectors achieved remarkably higher recognition accuracy than any of the three feature vectors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) handwritten numeral recognition / feature extraction / feature selection / Z1P code
Paper # PRU95-114
Date of Issue

Conference Information
Committee PRU
Conference Date 1995/9/28(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 Understanding (PRU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Synthesis of Feature Vector for Handwritten Numeral Recognition
Sub Title (in English)
Keyword(1) handwritten numeral recognition
Keyword(2) feature extraction
Keyword(3) feature selection
Keyword(4) Z1P code
1st Author's Name Shuji NISHIKAWA
1st Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University()
2nd Author's Name Tetsushi WAKABAYASHI
2nd Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University
3rd Author's Name Fumitaka KIMURA
3rd Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University
4th Author's Name Yasuji MIYAKE
4th Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University
5th Author's Name Toshio TSUTSUMIDA
5th Author's Affiliation Thechnology Department Research Center, Institute for Posts and Telecommunications Policy, Ministry of Posts and Telecommunication
Date 1995/9/28
Paper # PRU95-114
Volume (vol) vol.95
Number (no) 278
Page pp.pp.-
#Pages 6
Date of Issue