WEKO3
アイテム
色の恒常性を利用したCAPTCHAのユーザビリティと機械攻撃耐性向上のための検討
http://hdl.handle.net/10458/00010210
http://hdl.handle.net/10458/00010210ace6f490-4ba6-4cb4-b2b3-e9dff784822b
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2021-06-08 | |||||
タイトル | ||||||
タイトル | 色の恒常性を利用したCAPTCHAのユーザビリティと機械攻撃耐性向上のための検討 | |||||
言語 | ja | |||||
タイトル | ||||||
タイトル | A Study on Improving the Usability and Machine Resistance of Color Constancy CAPTCHA | |||||
言語 | en | |||||
言語 | ||||||
言語 | jpn | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | CAPTCHA | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | color constancy | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | gray-world | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | gray-scale | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | system usability score | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | departmental bulletin paper | |||||
著者 |
臼崎, 翔太郎
× 臼崎, 翔太郎× 砂本, 佑紀× 岡崎, 直宣× 山場, 久昭× 油田, 健太郎× 臼崎, 翔太郎× Sunamoto, Yuki |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | CAPTCHA is now widely used to prevent the bot from sending unauthorized service requests. CAPTCHA is a system that imposes tasks that are easy for humans and difficult for machines and thereby detect access from the bot. Unfortunately, many researchers have already reported that bots can break current CAPTCHAs by OCR and machine learning technology. Therefore, it is necessary to add interference for machine resistance. However, such interference also has a negative effect on human perception. Therefore, we adopt a color constancy to CAPTCHA. The color constancy is a human visual characteristic and is known to be difficult to reproduce mathematically. However, this CAPTCHA has a problem that human success is low and machine success rate is high. To solve this issue, we proposed an improved CAPTCHA by processing the base image and creating a new color interference filter. The first contrivance is to leave only a specific object color in the base image for defending the attack by the Gray-World algorithm, which is vulnerable to color bias. The second contrivance solves the weakness that the color filter does not always work effectively. We evaluated the effect of these devices on the accuracy rate of humans and machines and usability. | |||||
言語 | en | |||||
書誌情報 |
ja : 宮崎大学工学部紀要 en : Memoirs of Faculty of Engineering, University of Miyazaki 巻 49, p. 251-255, 発行日 2020-09-30 |
|||||
出版者 | ||||||
出版者 | 宮崎大学工学部 | |||||
言語 | ja | |||||
出版者 | ||||||
出版者 | Faculty of Engineering, University of Miyazaki | |||||
言語 | en | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 05404924 | |||||
書誌レコードID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA00732558 | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 |