2010年
The Evaluations of Deletion-Based Method and Mixing-Based Method for Audio CAPTCHAs
COMPUTERS HELPING PEOPLE WITH SPECIAL NEEDS, PROCEEDINGS, PT 1
- ,
- 巻
- 6179
- 号
- 開始ページ
- 368
- 終了ページ
- +
- 記述言語
- 英語
- 掲載種別
- 研究論文(国際会議プロシーディングス)
- DOI
- 10.1007/978-3-642-14097-6_59
- 出版者・発行元
- SPRINGER-VERLAG BERLIN
Audio CAPTCHA systems, which distinguish between software agents and human beings, are especially important for persons with visual disability. The popular approach is based on mixing-based methods (MBM), which use the mixed sounds of target speech and noises. We have proposed a deletion-based method (DBM) which uses the phonemic restoration effects. Our approach can control the difficulty of tasks simply by the masking ratio.
According to our design principle of CAPTCHA, the tasks should be designed so that the large difference of performance between the machines and human beings can be provided. In this paper, we show the experimental results that support the hypotheses as follows: (1) only using MBM, the degree of task difficulty can not be controlled easily, (2) using DBM, the degree of task difficulty and safeness of CAPTCHA system can be controlled easily.
According to our design principle of CAPTCHA, the tasks should be designed so that the large difference of performance between the machines and human beings can be provided. In this paper, we show the experimental results that support the hypotheses as follows: (1) only using MBM, the degree of task difficulty can not be controlled easily, (2) using DBM, the degree of task difficulty and safeness of CAPTCHA system can be controlled easily.
- リンク情報
-
- DOI
- https://doi.org/10.1007/978-3-642-14097-6_59
- DBLP
- https://dblp.uni-trier.de/rec/conf/icchp/NishimotoW10
- Web of Science
- https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000284033800059&DestApp=WOS_CPL
- URL
- http://dblp.uni-trier.de/db/conf/icchp/icchp2010.html#conf/icchp/NishimotoW10
- ID情報
-
- DOI : 10.1007/978-3-642-14097-6_59
- ISSN : 0302-9743
- DBLP ID : conf/icchp/NishimotoW10
- Web of Science ID : WOS:000284033800059