scispace - formally typeset
Proceedings ArticleDOI

Effective CAPTCHA with Amodal Completion and Aftereffects by Complementary Colors and Difference of Luminance

Reads0
Chats0
TLDR
An effective CAPTCHA with amodal completion and aftereffects is proposed and improved by applying complementary colors and difference of luminance and adding colors to the algorithm with considering combinations of complementary Colors and those of Luminance.
Abstract
We propose an effective CAPTCHA with amodalcompletion and aftereffects and improve it by applying complementary colors and difference of luminance. CAPTCHA is a method which distinguishes human beings from artificial intelligence which is usually called bots on Internet. Bots acquire accounts of web services for unfair uses such as stealth marketing or SPAM attacks. That is, CAPTCHA is a countermeasure against those attacks. The most popular kind of CAPTCHA methods is text-based CAPTCHA in which distorted alphabets and numbers appear with obstacles or noise. However, it is known that all of text-based CAPTCHA algorithms can be analyzed by computers. In addition, too much distortion or noise prevents human beings from alphabets or numbers. There are other kinds of CAPTCHA methods such as image CAPTCHA and audio CAPTCHA. However, they also have problems in use. As a related work, an effective text-based CAPTCHA algorithm with amodal completion was proposed. The CAPTCHA provides computers a large amount of calculation cost while amodal completion helps human beings to recognize characters momentarily. On the other hand, extreme concentration is required for momentary recognition. The CAPTCHA is once improved in our laboratory. Aftereffects are additionally combined with the CAPTCHA algorithm. Moreover, in this paper, we add colors to the algorithm with considering combinations of complementary colors and those of luminance. The aftereffects extend time for recognition of characters from a moment to several seconds.

read more

Citations
More filters
Proceedings ArticleDOI

Challenge of Deep Learning against CAPTCHA with Amodal Completion and Aftereffects by Colors

TL;DR: This paper evaluates the proposed text-based CAPTCHA algorithm with amodal completion since machine learning is faster and more accurate than existing calculations by a computer and confirms the limitations of machine learning.
Proceedings ArticleDOI

Challenge to Impede Deep Learning against CAPTCHA with Ergonomic Design

TL;DR: Jagged lines to edges of characters are added since edges are one of the most important parts for recognition in deep learning since deep learning is faster and more accurate than existing methods for recognition with computers.
Proceedings ArticleDOI

Deep Learning Analysis of Amodal Completion CAPTCHA with Colors and Hidden Positions

TL;DR: This study proposed a CAPTCHA method with amodal Completion in order to prevent computers from readingCAPTCHA and discovered the undetermined element and problems in this research.
Proceedings ArticleDOI

CAPTCHA characters recognition based on image processing and support vector machine algorithms

Yi Qiu
TL;DR: In this paper , the authors presented an approach to recognize text-based CAPTCHAs based on image processing and support vector machine algorithms, and tested the simple test-based CA-CHAs, the experimental results show that the approach has an efficient recognition.
References
More filters
Proceedings ArticleDOI

Recognizing objects in adversarial clutter: breaking a visual CAPTCHA

TL;DR: Efficient methods based on shape context matching are developed 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.
Proceedings Article

Using Machine Learning to Break Visual Human Interaction Proofs (HIPs)

TL;DR: This paper studied various Human Interactive Proofs (HIPs) on the market, and found that most HIPs are pure recognition tasks which can easily be broken using machine learning.
Proceedings Article

Computers beat Humans at Single Character Recognition in Reading based Human Interaction Proofs (HIPs)

TL;DR: Comparisons of human and computer single character recognition abilities through a sequence of human user studies and computer experiments using convolutional neural networks show that computers are as good as or better than humans at one character recognition under all commonly used distortion and clutter scenarios used in todays HIPs.
Journal ArticleDOI

Recognition of partly occluded patterns: a neural network model.

TL;DR: A hypothesis explaining why a pattern is easier to recognize when it is occluded by visible objects than by invisible opaque objects is proposed and a neural network model is constructed based on this hypothesis.
Proceedings ArticleDOI

Proposal of Movie CAPTCHA Method Using Amodal Completion

TL;DR: This paper proposes a practical method for CAPTCHA in which only humans can provide correct answers by applying a modal completion, which has a higher success rate than humans.