Detail publikace

Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms

BOŠTÍK, O. KLEČKA, J.

Originální název

Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms

Anglický název

Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms

Jazyk

en

Originální abstrakt

The focus of this paper is to compare several common machine learning classi cation algorithms for Optical Character Recognition of CAPTCHA codes. The main part of a research focuses on the comparative study of Neural Networks, k-Nearest Neighbour, Support Vector Machines and Decision Trees implemented in MATLAB Computing environment. Achieved success rates of all analyzed algorithms overcome 89%. The main di erence in results of used algorithms is within the learning times. Based on the data found, it is possible to choose the right algorithm for the particular task.

Anglický abstrakt

The focus of this paper is to compare several common machine learning classi cation algorithms for Optical Character Recognition of CAPTCHA codes. The main part of a research focuses on the comparative study of Neural Networks, k-Nearest Neighbour, Support Vector Machines and Decision Trees implemented in MATLAB Computing environment. Achieved success rates of all analyzed algorithms overcome 89%. The main di erence in results of used algorithms is within the learning times. Based on the data found, it is possible to choose the right algorithm for the particular task.

Dokumenty

BibTex


@inproceedings{BUT147094,
  author="Ondřej {Boštík} and Jan {Klečka}",
  title="Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms",
  annote="The focus of this paper is to compare several common machine learning classication
algorithms for Optical Character Recognition of CAPTCHA codes. The main part of a research
focuses on the comparative study of Neural Networks, k-Nearest Neighbour, Support Vector
Machines and Decision Trees implemented in MATLAB Computing environment. Achieved
success rates of all analyzed algorithms overcome 89%. The main dierence in results of used
algorithms is within the learning times. Based on the data found, it is possible to choose the
right algorithm for the particular task.",
  booktitle="15th IFAC Conference on Programmable Devices and Embedded Systems - PDeS 2018",
  chapter="147094",
  doi="10.1016/j.ifacol.2018.07.155",
  howpublished="electronic, physical medium",
  number="15",
  year="2018",
  month="april",
  pages="208--213",
  type="conference paper"
}