Application of the violajones algorithm, hough transform and artificial neural networks for recognition character information on a complex background

A. A. Druki, P. A. Kakovkin, D. S. Cherneta

Research output: Contribution to journalArticle

Abstract

The work is dedicated to development of algorithms to increase the efficiency of character recognition on a complex background with noise, affine and projective distortions. The paper proposes an approach to solving the problem of character recognition, which includes three main stages: detection of region character locations in the image; image normalization and selection of individual characters; character recognition. The ViolaJones algorithm realization is proposed for detecting of the characters' region in images with complex background. Image normalization includes the following operations: selection borders, Hough transform, closed contours search, image alignment. The search of characters string horizontal edges in the image is performed by using the Hough transform. The detection of individual characters' regions is performed by using the closed contours search. The configuration of convolution neural network is proposed for character recognition. The testing results of the developed algorithms efficiency and their comparison with existing analogues are presented. On the basis of the approach, the software system which shows the high efficiency of character recognition on a complex background intended to recognize the car number plates in the images was developed.

Original languageEnglish
Pages (from-to)65-77
Number of pages13
JournalScientific Visualization
Volume8
Issue number3
Publication statusPublished - 2016

Fingerprint

Character recognition
Hough transforms
Neural networks
Convolution
Railroad cars
Testing

Keywords

  • Artificial neural networks
  • Character recognition
  • Hough transform
  • Image processing
  • Violajones algorithm

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Application of the violajones algorithm, hough transform and artificial neural networks for recognition character information on a complex background. / Druki, A. A.; Kakovkin, P. A.; Cherneta, D. S.

In: Scientific Visualization, Vol. 8, No. 3, 2016, p. 65-77.

Research output: Contribution to journalArticle

@article{de82b34a7ae9447ebaf1969d32c48dfb,
title = "Application of the violajones algorithm, hough transform and artificial neural networks for recognition character information on a complex background",
abstract = "The work is dedicated to development of algorithms to increase the efficiency of character recognition on a complex background with noise, affine and projective distortions. The paper proposes an approach to solving the problem of character recognition, which includes three main stages: detection of region character locations in the image; image normalization and selection of individual characters; character recognition. The ViolaJones algorithm realization is proposed for detecting of the characters' region in images with complex background. Image normalization includes the following operations: selection borders, Hough transform, closed contours search, image alignment. The search of characters string horizontal edges in the image is performed by using the Hough transform. The detection of individual characters' regions is performed by using the closed contours search. The configuration of convolution neural network is proposed for character recognition. The testing results of the developed algorithms efficiency and their comparison with existing analogues are presented. On the basis of the approach, the software system which shows the high efficiency of character recognition on a complex background intended to recognize the car number plates in the images was developed.",
keywords = "Artificial neural networks, Character recognition, Hough transform, Image processing, Violajones algorithm",
author = "Druki, {A. A.} and Kakovkin, {P. A.} and Cherneta, {D. S.}",
year = "2016",
language = "English",
volume = "8",
pages = "65--77",
journal = "Scientific Visualization",
issn = "2079-3537",
publisher = "National Research Nuclear University {"}MEPhI{"}",
number = "3",

}

TY - JOUR

T1 - Application of the violajones algorithm, hough transform and artificial neural networks for recognition character information on a complex background

AU - Druki, A. A.

AU - Kakovkin, P. A.

AU - Cherneta, D. S.

PY - 2016

Y1 - 2016

N2 - The work is dedicated to development of algorithms to increase the efficiency of character recognition on a complex background with noise, affine and projective distortions. The paper proposes an approach to solving the problem of character recognition, which includes three main stages: detection of region character locations in the image; image normalization and selection of individual characters; character recognition. The ViolaJones algorithm realization is proposed for detecting of the characters' region in images with complex background. Image normalization includes the following operations: selection borders, Hough transform, closed contours search, image alignment. The search of characters string horizontal edges in the image is performed by using the Hough transform. The detection of individual characters' regions is performed by using the closed contours search. The configuration of convolution neural network is proposed for character recognition. The testing results of the developed algorithms efficiency and their comparison with existing analogues are presented. On the basis of the approach, the software system which shows the high efficiency of character recognition on a complex background intended to recognize the car number plates in the images was developed.

AB - The work is dedicated to development of algorithms to increase the efficiency of character recognition on a complex background with noise, affine and projective distortions. The paper proposes an approach to solving the problem of character recognition, which includes three main stages: detection of region character locations in the image; image normalization and selection of individual characters; character recognition. The ViolaJones algorithm realization is proposed for detecting of the characters' region in images with complex background. Image normalization includes the following operations: selection borders, Hough transform, closed contours search, image alignment. The search of characters string horizontal edges in the image is performed by using the Hough transform. The detection of individual characters' regions is performed by using the closed contours search. The configuration of convolution neural network is proposed for character recognition. The testing results of the developed algorithms efficiency and their comparison with existing analogues are presented. On the basis of the approach, the software system which shows the high efficiency of character recognition on a complex background intended to recognize the car number plates in the images was developed.

KW - Artificial neural networks

KW - Character recognition

KW - Hough transform

KW - Image processing

KW - Violajones algorithm

UR - http://www.scopus.com/inward/record.url?scp=84979000009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979000009&partnerID=8YFLogxK

M3 - Article

VL - 8

SP - 65

EP - 77

JO - Scientific Visualization

JF - Scientific Visualization

SN - 2079-3537

IS - 3

ER -