Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network

Polina M. Osina, Yuliya A. Bolotova, Vladimir G. Spitsyn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work we present algorithms which are applied in such task as text recognition on images and video. Proposed algorithm is based on the combination of discrete cosine transform and convolutional neural networks. Description of the applying features of discrete cosine transform for text detection is provided. We list the main advantages and disadvantages of CNN and DCT combination. Also in this article we are going to consider methods of convolution neural networks for the task of text recognition.

Original languageEnglish
Title of host publication2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509010806
DOIs
Publication statusPublished - 31 Jul 2017
Event2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Astana, Kazakhstan
Duration: 29 Jun 201730 Jun 2017

Conference

Conference2017 International Siberian Conference on Control and Communications, SIBCON 2017
CountryKazakhstan
CityAstana
Period29.6.1730.6.17

Fingerprint

Discrete Cosine Transform
Discrete cosine transforms
Neural Networks
Neural networks
Convolution
Text

Keywords

  • artificial neural network
  • convolution neural networks
  • discrete cosine transform
  • machine learning
  • optical character recognition
  • Text detection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Control and Optimization
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Osina, P. M., Bolotova, Y. A., & Spitsyn, V. G. (2017). Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network. In 2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings [7998591] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIBCON.2017.7998591

Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network. / Osina, Polina M.; Bolotova, Yuliya A.; Spitsyn, Vladimir G.

2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 7998591.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Osina, PM, Bolotova, YA & Spitsyn, VG 2017, Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network. in 2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings., 7998591, Institute of Electrical and Electronics Engineers Inc., 2017 International Siberian Conference on Control and Communications, SIBCON 2017, Astana, Kazakhstan, 29.6.17. https://doi.org/10.1109/SIBCON.2017.7998591
Osina PM, Bolotova YA, Spitsyn VG. Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network. In 2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. 7998591 https://doi.org/10.1109/SIBCON.2017.7998591
Osina, Polina M. ; Bolotova, Yuliya A. ; Spitsyn, Vladimir G. / Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network. 2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{30e3678820864e4d8c2627346bc534b3,
title = "Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network",
abstract = "In this work we present algorithms which are applied in such task as text recognition on images and video. Proposed algorithm is based on the combination of discrete cosine transform and convolutional neural networks. Description of the applying features of discrete cosine transform for text detection is provided. We list the main advantages and disadvantages of CNN and DCT combination. Also in this article we are going to consider methods of convolution neural networks for the task of text recognition.",
keywords = "artificial neural network, convolution neural networks, discrete cosine transform, machine learning, optical character recognition, Text detection",
author = "Osina, {Polina M.} and Bolotova, {Yuliya A.} and Spitsyn, {Vladimir G.}",
year = "2017",
month = "7",
day = "31",
doi = "10.1109/SIBCON.2017.7998591",
language = "English",
booktitle = "2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network

AU - Osina, Polina M.

AU - Bolotova, Yuliya A.

AU - Spitsyn, Vladimir G.

PY - 2017/7/31

Y1 - 2017/7/31

N2 - In this work we present algorithms which are applied in such task as text recognition on images and video. Proposed algorithm is based on the combination of discrete cosine transform and convolutional neural networks. Description of the applying features of discrete cosine transform for text detection is provided. We list the main advantages and disadvantages of CNN and DCT combination. Also in this article we are going to consider methods of convolution neural networks for the task of text recognition.

AB - In this work we present algorithms which are applied in such task as text recognition on images and video. Proposed algorithm is based on the combination of discrete cosine transform and convolutional neural networks. Description of the applying features of discrete cosine transform for text detection is provided. We list the main advantages and disadvantages of CNN and DCT combination. Also in this article we are going to consider methods of convolution neural networks for the task of text recognition.

KW - artificial neural network

KW - convolution neural networks

KW - discrete cosine transform

KW - machine learning

KW - optical character recognition

KW - Text detection

UR - http://www.scopus.com/inward/record.url?scp=85028506328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028506328&partnerID=8YFLogxK

U2 - 10.1109/SIBCON.2017.7998591

DO - 10.1109/SIBCON.2017.7998591

M3 - Conference contribution

AN - SCOPUS:85028506328

BT - 2017 International Siberian Conference on Control and Communications, SIBCON 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -