Presentation 2010-03-16
Chinese Cursive Script Image Retrieval System Using Many Ancient Text
Takaaki ISHIMARU, Takeshi NAGASAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Chinese cursive script is complex shape, so Chinese cursive script retrieval is difficult that general character retrieve. It is necessary that many dictionary data is registered and data retrieve at high speed to construct the system that retrieve Chinese cursive script. When the machine retrieve that script, calculate feature quantity, evaluate similarity. In this research, we use the feature vector that is Histogram of Oriented Gradients (HOG). we use Locality Sensitive Hashing (LSH) to retrieve Chinese cursive script in high speed. The computer retrieve each character to cut other text using this system, target high speed retrieval and high recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) HOG / Chinese Cursive Script / LSH / Character Retrieval
Paper # PRMU2009-325,HIP2009-210
Date of Issue

Conference Information
Committee PRMU
Conference Date 2010/3/8(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) Chinese Cursive Script Image Retrieval System Using Many Ancient Text
Sub Title (in English)
Keyword(1) HOG
Keyword(2) Chinese Cursive Script
Keyword(3) LSH
Keyword(4) Character Retrieval
1st Author's Name Takaaki ISHIMARU
1st Author's Affiliation Future University-Hakodate()
2nd Author's Name Takeshi NAGASAKI
2nd Author's Affiliation Future University-Hakodate
Date 2010-03-16
Paper # PRMU2009-325,HIP2009-210
Volume (vol) vol.109
Number (no) 470
Page pp.pp.-
#Pages 6
Date of Issue