Recognizing objects in adversarial clutter: breaking a visual CAPTCHA
By Greg Mori, Jitendra Malik. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003
714 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Information Systems
View Paper: https://www.semanticscholar.org/paper/310dda18ecb3817aef260239f43a7821faf4cf55
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Jitendra Malik
- Trevor Darrell
- Xiaogang Wang
- Li Fei-Fei
- Andrew Zisserman
In Information Systems
- Greg Mori
- Jitendra Malik
- Haibin Ling
- Elie Bursztein
- John C. Mitchell
- Serge J. Belongie
- Kai Wang
- Kazunori Okada
Citations in the corpus
- The End is Nigh: Generic Solving of Text-based CAPTCHAs (2014, background): “This approach, known as the segment then recognize approach and illustrated in figure 2, works equally well on image and audio captchas (see [37, 13, 43, 47, 9, 8, 15]).”
- Shape Classification Using the Inner-Distance (2007, background): “Some examples can be found in [33], [43], [44], [47], [34], [26].”
- Image retrieval: Ideas, influences, and trends of the new age (2008, background): “Recently, a number of OCR-based techniques have been proposed to break text-based CAPTCHAs [Mori and Malik 2003].”
- Using Machine Learning to Break Visual Human Interaction Proofs (HIPs) (2004, background): “[7] Mori G, Malik J (2003), “Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA,” Proc.”
- Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs (2013, methodology): “For example, in our text application, the Sis include binary indicators for the presence or absence of each glyph, along with its identity (“A“ through ”Z”, plus digits 0-9), and parameters including location,”
- Telling humans and computers apart automatically (2004, methodology): “Malik and Mori s algorithm represents significant progress in the general area of text recognition, and it is extremely encouraging to see such progress.”
- I am Robot: (Deep) Learning to Break Semantic Image CAPTCHAs (2016, methodology): “Mori and Malik [30] presented two methods for breaking the EZ-Gimpy and Gimpy captchas that depict words over artificial noise, achieving a success rate of 92% and 33% respectively.”
- Usability of CAPTCHAs or usability issues in CAPTCHA design (2008, background): “[ 12 , 15]). However, we are not convinced that it is absolutely a bad idea to make use of lexical information in CAPTCHA schemes.”
- Recovering 3D human body configurations using shape contexts (2006, methodology): “In later work [36], we extended the shape context descriptor by encoding more descriptive information than point counts in the histogram bins.”
- Machine learning attacks against the Asirra CAPTCHA (2008, neutral): “We conclude in section 4.”
- An Efficient Earth Mover's Distance Algorithm for Robust Histogram Comparison (2007, methodology): “Unlike the above previous work, we focus on designing a distance metric for histogram-based local descriptors, which have attracted a lot of research interests recently [3], [32], [47], [48], [26], [29], [21], [34], [31].”
- Asirra: a CAPTCHA that exploits interest-aligned manual image categorization (2007, background): “Mori and Malik demonstrated that von Ahn’s original GIMPY CAPTCHA [13] can be solved automatically 92% of the time [8].”
- Word Spotting in the Wild (2010, methodology): “The works that are most similar to ours are that of [13] and [5].”