Automatic text extraction in news images using morphology

Inyoung Jang, Byoung Chul Ko, Hyeran Byun, Yeongwoo Choi

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

In this paper we present a new method to extract both superimposed and embedded graphical texts in a freeze-frame of news video. The algorithm is summarized in the following three steps. For the first step, we convert a color image into a gray-level image and apply contrast stretching to enhance the contrast of the input image. Then, a modified local adaptive thresholding is applied to the contrast-stretched image. The second step is divided into three processes: eliminating text-like components by applying erosion, dilation, and (OpenClose + CloseOpen)/2 morphological operations, maintaining text components using (OpenClose + CloseOpen)/2 operation with a new Geo-correction method, and subtracting two result images for eliminating false-positive components farther. In the third filtering step, the characteristics of each component such as the ratio of the number of pixels in each candidate component to the number of its boundary pixels and the ratio of the minor to the major axis of each bounding box are used. Acceptable results have been obtained using the proposed method on 300 news images with a recognition rate of 93.6%. Also, our method indicates a good performance on all the various kinds of images by adjusting the size of the structuring element.

Original languageEnglish
Pages (from-to)521-530
Number of pages10
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume4671 I
DOIs
Publication statusPublished - 2002 Jan 1
EventViual Communications and Image Processing 2002 - San Jose, CA, United States
Duration: 2002 Jan 212002 Jan 23

Fingerprint

news
Pixels
Stretching
image contrast
Erosion
Color
pixels
Pixel
Adaptive Thresholding
Morphological Operations
erosion
boxes
Color Image
Dilation
False Positive
adjusting
Convert
Text
Minor
color

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{73b94a6f30c04ad0a85f7f7faa6017c5,
title = "Automatic text extraction in news images using morphology",
abstract = "In this paper we present a new method to extract both superimposed and embedded graphical texts in a freeze-frame of news video. The algorithm is summarized in the following three steps. For the first step, we convert a color image into a gray-level image and apply contrast stretching to enhance the contrast of the input image. Then, a modified local adaptive thresholding is applied to the contrast-stretched image. The second step is divided into three processes: eliminating text-like components by applying erosion, dilation, and (OpenClose + CloseOpen)/2 morphological operations, maintaining text components using (OpenClose + CloseOpen)/2 operation with a new Geo-correction method, and subtracting two result images for eliminating false-positive components farther. In the third filtering step, the characteristics of each component such as the ratio of the number of pixels in each candidate component to the number of its boundary pixels and the ratio of the minor to the major axis of each bounding box are used. Acceptable results have been obtained using the proposed method on 300 news images with a recognition rate of 93.6{\%}. Also, our method indicates a good performance on all the various kinds of images by adjusting the size of the structuring element.",
author = "Inyoung Jang and Ko, {Byoung Chul} and Hyeran Byun and Yeongwoo Choi",
year = "2002",
month = "1",
day = "1",
doi = "10.1117/12.453094",
language = "English",
volume = "4671 I",
pages = "521--530",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

Automatic text extraction in news images using morphology. / Jang, Inyoung; Ko, Byoung Chul; Byun, Hyeran; Choi, Yeongwoo.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 4671 I, 01.01.2002, p. 521-530.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Automatic text extraction in news images using morphology

AU - Jang, Inyoung

AU - Ko, Byoung Chul

AU - Byun, Hyeran

AU - Choi, Yeongwoo

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper we present a new method to extract both superimposed and embedded graphical texts in a freeze-frame of news video. The algorithm is summarized in the following three steps. For the first step, we convert a color image into a gray-level image and apply contrast stretching to enhance the contrast of the input image. Then, a modified local adaptive thresholding is applied to the contrast-stretched image. The second step is divided into three processes: eliminating text-like components by applying erosion, dilation, and (OpenClose + CloseOpen)/2 morphological operations, maintaining text components using (OpenClose + CloseOpen)/2 operation with a new Geo-correction method, and subtracting two result images for eliminating false-positive components farther. In the third filtering step, the characteristics of each component such as the ratio of the number of pixels in each candidate component to the number of its boundary pixels and the ratio of the minor to the major axis of each bounding box are used. Acceptable results have been obtained using the proposed method on 300 news images with a recognition rate of 93.6%. Also, our method indicates a good performance on all the various kinds of images by adjusting the size of the structuring element.

AB - In this paper we present a new method to extract both superimposed and embedded graphical texts in a freeze-frame of news video. The algorithm is summarized in the following three steps. For the first step, we convert a color image into a gray-level image and apply contrast stretching to enhance the contrast of the input image. Then, a modified local adaptive thresholding is applied to the contrast-stretched image. The second step is divided into three processes: eliminating text-like components by applying erosion, dilation, and (OpenClose + CloseOpen)/2 morphological operations, maintaining text components using (OpenClose + CloseOpen)/2 operation with a new Geo-correction method, and subtracting two result images for eliminating false-positive components farther. In the third filtering step, the characteristics of each component such as the ratio of the number of pixels in each candidate component to the number of its boundary pixels and the ratio of the minor to the major axis of each bounding box are used. Acceptable results have been obtained using the proposed method on 300 news images with a recognition rate of 93.6%. Also, our method indicates a good performance on all the various kinds of images by adjusting the size of the structuring element.

UR - http://www.scopus.com/inward/record.url?scp=0036028958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036028958&partnerID=8YFLogxK

U2 - 10.1117/12.453094

DO - 10.1117/12.453094

M3 - Conference article

AN - SCOPUS:0036028958

VL - 4671 I

SP - 521

EP - 530

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -