Recognizing objects in adversarial clutter: breaking a visual CAPTCHA
Top Cited Papers
- 20 November 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 134
- https://doi.org/10.1109/cvpr.2003.1211347
Abstract
In 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 (see Fig. 1, 5), currently used by Yahoo, and Gimpy (Fig. 2, 9) 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 EZGimpy 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.Keywords
This publication has 13 references indexed in Scilit:
- Shape contexts enable efficient retrieval of similar shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- BaffleText: a Human Interactive ProofPublished by SPIE-Intl Soc Optical Eng ,2003
- Toward island-of-reliability-driven very-large-vocabulary on-line handwriting recognition using character confidence scoringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Layer extraction from multiple images containing reflections and transparencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Shape matching and object recognition using shape contextsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Model-based classification treesIEEE Transactions on Information Theory, 2001
- The role of holistic paradigms in handwritten word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Online and off-line handwriting recognition: a comprehensive surveyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Affine invariant model-based object recognitionIEEE Transactions on Robotics and Automation, 1990