Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/399213
Full metadata record
DC FieldValueLanguage
dc.contributorMori, Gregen_US
dc.contributorMalik, J.en_US
dc.date2003en_US
dc.date.accessioned2020-05-18T11:34:33Z-
dc.date.available2020-05-18T11:34:33Z-
dc.date.issued2008en_US
dc.identifier.issn0-7695-1900-8en_US
dc.identifier.other10.1109/CVPR.2003.1211347en_US
dc.identifier.urihttp://localhost/handle/Hannan/367388en_US
dc.identifier.urihttp://localhost/handle/Hannan/399213-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZ-Gimpy, examples of visual CAPTCHAs. A CAPTCHA ("Completely Automated Public Turing test to Tell Computers and Humans Apart") is a program that can generate and grade tests that most humans can pass, yet current computer programs can't pass. EZ-Gimpy, currently used by Yahoo, and Gimpy are CAPTCHAs based on word recognition in the presence of clutter. These CAPTCHAs provide excellent test sets since the clutter they contain is adversarial; it is designed to confuse computer programs. We have developed efficient methods based on shape context matching that can identify the word in an EZ-Gimpy image with a success rate of 92%, and the requisite 3 words in a Gimpy image 33% of the time. The problem of identifying words in such severe clutter provides valuable insight into the more general problem of object recognition in scenes. The methods that we present are instances of a framework designed to tackle this general problem.en_US
dc.relation.haspartAL505337.pdfen_US
dc.subjectScience & Technologyen_US
dc.titleRecognizing objects in adversarial clutter: breaking a visual CAPTCHAen_US
dc.typeArticleen_US
dc.journal.title2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.en_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL505337.pdf536.92 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorMori, Gregen_US
dc.contributorMalik, J.en_US
dc.date2003en_US
dc.date.accessioned2020-05-18T11:34:33Z-
dc.date.available2020-05-18T11:34:33Z-
dc.date.issued2008en_US
dc.identifier.issn0-7695-1900-8en_US
dc.identifier.other10.1109/CVPR.2003.1211347en_US
dc.identifier.urihttp://localhost/handle/Hannan/367388en_US
dc.identifier.urihttp://localhost/handle/Hannan/399213-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZ-Gimpy, examples of visual CAPTCHAs. A CAPTCHA ("Completely Automated Public Turing test to Tell Computers and Humans Apart") is a program that can generate and grade tests that most humans can pass, yet current computer programs can't pass. EZ-Gimpy, currently used by Yahoo, and Gimpy are CAPTCHAs based on word recognition in the presence of clutter. These CAPTCHAs provide excellent test sets since the clutter they contain is adversarial; it is designed to confuse computer programs. We have developed efficient methods based on shape context matching that can identify the word in an EZ-Gimpy image with a success rate of 92%, and the requisite 3 words in a Gimpy image 33% of the time. The problem of identifying words in such severe clutter provides valuable insight into the more general problem of object recognition in scenes. The methods that we present are instances of a framework designed to tackle this general problem.en_US
dc.relation.haspartAL505337.pdfen_US
dc.subjectScience & Technologyen_US
dc.titleRecognizing objects in adversarial clutter: breaking a visual CAPTCHAen_US
dc.typeArticleen_US
dc.journal.title2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.en_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL505337.pdf536.92 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorMori, Gregen_US
dc.contributorMalik, J.en_US
dc.date2003en_US
dc.date.accessioned2020-05-18T11:34:33Z-
dc.date.available2020-05-18T11:34:33Z-
dc.date.issued2008en_US
dc.identifier.issn0-7695-1900-8en_US
dc.identifier.other10.1109/CVPR.2003.1211347en_US
dc.identifier.urihttp://localhost/handle/Hannan/367388en_US
dc.identifier.urihttp://localhost/handle/Hannan/399213-
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractIn this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZ-Gimpy, examples of visual CAPTCHAs. A CAPTCHA ("Completely Automated Public Turing test to Tell Computers and Humans Apart") is a program that can generate and grade tests that most humans can pass, yet current computer programs can't pass. EZ-Gimpy, currently used by Yahoo, and Gimpy are CAPTCHAs based on word recognition in the presence of clutter. These CAPTCHAs provide excellent test sets since the clutter they contain is adversarial; it is designed to confuse computer programs. We have developed efficient methods based on shape context matching that can identify the word in an EZ-Gimpy image with a success rate of 92%, and the requisite 3 words in a Gimpy image 33% of the time. The problem of identifying words in such severe clutter provides valuable insight into the more general problem of object recognition in scenes. The methods that we present are instances of a framework designed to tackle this general problem.en_US
dc.relation.haspartAL505337.pdfen_US
dc.subjectScience & Technologyen_US
dc.titleRecognizing objects in adversarial clutter: breaking a visual CAPTCHAen_US
dc.typeArticleen_US
dc.journal.title2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.en_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL505337.pdf536.92 kBAdobe PDF