Presentation 2019-08-10
A System to Acquire Expiration Date of Merchandise for Visually Impaired People
Takeuchi Yoshinori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have been researching a system to acquire expiration date of Merchandise for visually impaired people. In this paper, we aim to improve the recognition rate of the conventional expiration date acquisition system by machine learning technology. In order to limit the printed part of expiration date, characters of “kigen(期限)” or “gen(限)” are learned by machine learning, and we compare the recognition results. Compared with 78.6% recognition rate in the conventional method that used SVM for recognition, the recognition rate of “kigen(期限)” for the images taken from the front was 84% and the recognition rate of “gen(限)” from the images taken for various angles was 78.9%. The recognition rate of expiration date was 40% in conventional method that used a commercially available OCR library, whereas it was 100% for the images taken from the front and 40% for the images taken from various angles.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) visual impairment / visual substitution / machine learning / character recognition
Paper # WIT2019-13
Date of Issue 2019-08-03 (WIT)

Conference Information
Committee WIT
Conference Date 2019/8/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Teikyo University, Utsunomiya Campus (TBD)
Topics (in Japanese) (See Japanese page)
Topics (in English) Well-being Information Technology, etc.
Chair Daisuke Wakatsuki(Tsukuba Univ. of Tech.)
Vice Chair Shinji Sakou(Nagoya Inst. of Tech.)
Secretary Shinji Sakou(Saitama Industrial Tech. Center)
Assistant Manabi Miyagi(Tsukuba Univ. of Tech.) / Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.)

Paper Information
Registration To Technical Committee on Well-being Information Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A System to Acquire Expiration Date of Merchandise for Visually Impaired People
Sub Title (in English) a discussion about improvement of recognition rate with machine learning
Keyword(1) visual impairment
Keyword(2) visual substitution
Keyword(3) machine learning
Keyword(4) character recognition
1st Author's Name Takeuchi Yoshinori
1st Author's Affiliation Daido University(Daido Univ.)
Date 2019-08-10
Paper # WIT2019-13
Volume (vol) vol.119
Number (no) WIT-165
Page pp.pp.23-28(WIT),
#Pages 6
Date of Issue 2019-08-03 (WIT)