Presentation 2015-12-04
Scene Text Localization Using Object Detection Based on Filtered Feature Channels and Crosswise Region Merging
Takuro Oki, Ryusuke Miyamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a novel scene text recognition scheme using a detector constructed by the Filtered Feature Channels and cross wise region merging. Experimental results using the ICDAR2013 data set show that the precision and the recall by the scheme becomes 61.77 and 60.30, respectively, while our old scheme using the Integral Channel Features shows 49.65 and 48.52, respectively. This results is much better than baseline and near to some schemes ranked in the ICDAR2013 competition even though the scheme does not apply post-processing using multi-class classifier to recognize what characters are.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) visual object detection / scene text localization / scene text recognition
Paper # SIS2015-47
Date of Issue 2015-11-26 (SIS)

Conference Information
Committee SIS
Conference Date 2015/12/3(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Matsuya-sensen (Awara city, Fukui)
Topics (in Japanese) (See Japanese page)
Topics (in English) SoC, Related to RFID, etc.
Chair Mitsuji Muneyasu(Kansai Univ.)
Vice Chair Hirokazu Tanaka(Hiroshima City Univ.) / Takayuki Nakachi(NTT)
Secretary Hirokazu Tanaka(Nagoya City Univ.) / Takayuki Nakachi(Toshiba)
Assistant Hiroyuki Tsuji(Kanagawa Inst. of Tech.) / Hakaru Tamukoh(Kyushu Inst. of Tech.)

Paper Information
Registration To Technical Committee on Smart Info-Media System
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Scene Text Localization Using Object Detection Based on Filtered Feature Channels and Crosswise Region Merging
Sub Title (in English)
Keyword(1) visual object detection
Keyword(2) scene text localization
Keyword(3) scene text recognition
1st Author's Name Takuro Oki
1st Author's Affiliation Meiji University(Meiji Univ.)
2nd Author's Name Ryusuke Miyamoto
2nd Author's Affiliation Meiji University(Meiji Univ.)
Date 2015-12-04
Paper # SIS2015-47
Volume (vol) vol.115
Number (no) SIS-348
Page pp.pp.99-104(SIS),
#Pages 6
Date of Issue 2015-11-26 (SIS)