Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features

In this article, a new approach is proposed for text detection, extraction and inpainting in color images. The proposed algorithm includes three stages. In the first stage, several gradient based operators and image corners are utilized to localize text blocks. We use a new block split and merging a...

Full description

Bibliographic Details
Main Authors: Mohammad Khodadadi Azadboni, Alireza Behrad
Format: Article
Language:English
Published: Iran Telecom Research Center 2015-06-01
Series:International Journal of Information and Communication Technology Research
Subjects:
Online Access:http://ijict.itrc.ac.ir/article-1-99-en.html
_version_ 1811169276569059328
author Mohammad Khodadadi Azadboni
Alireza Behrad
author_facet Mohammad Khodadadi Azadboni
Alireza Behrad
author_sort Mohammad Khodadadi Azadboni
collection DOAJ
description In this article, a new approach is proposed for text detection, extraction and inpainting in color images. The proposed algorithm includes three stages. In the first stage, several gradient based operators and image corners are utilized to localize text blocks. We use a new block split and merging algorithm to enhance the accuracy of text localization algorithm. An SVM based text verification algorithm is then employed with a new set of features to reject non-text blocks. To inpaint text areas, we cluster different colors in the text blocks using k-means clustering algorithm and estimate background and text colors. Then a color segmentation algorithm is employed to detect characters’ pixels accurately. In the third stage, the proposed inpainting algorithm is applied to restore initial image contents. The inpainting algorithm is based on a matching algorithm that considers the priority for inpainting the pixels. Experimental results and a comparison of the results with those of other methods show the efficiency of the proposed algorithm.
first_indexed 2024-04-10T16:39:41Z
format Article
id doaj.art-1ea768cce023417ab837a40e980b6d6c
institution Directory Open Access Journal
issn 2251-6107
2783-4425
language English
last_indexed 2024-04-10T16:39:41Z
publishDate 2015-06-01
publisher Iran Telecom Research Center
record_format Article
series International Journal of Information and Communication Technology Research
spelling doaj.art-1ea768cce023417ab837a40e980b6d6c2023-02-08T07:54:43ZengIran Telecom Research CenterInternational Journal of Information and Communication Technology Research2251-61072783-44252015-06-01721931Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural FeaturesMohammad Khodadadi Azadboni0Alireza Behrad1 In this article, a new approach is proposed for text detection, extraction and inpainting in color images. The proposed algorithm includes three stages. In the first stage, several gradient based operators and image corners are utilized to localize text blocks. We use a new block split and merging algorithm to enhance the accuracy of text localization algorithm. An SVM based text verification algorithm is then employed with a new set of features to reject non-text blocks. To inpaint text areas, we cluster different colors in the text blocks using k-means clustering algorithm and estimate background and text colors. Then a color segmentation algorithm is employed to detect characters’ pixels accurately. In the third stage, the proposed inpainting algorithm is applied to restore initial image contents. The inpainting algorithm is based on a matching algorithm that considers the priority for inpainting the pixels. Experimental results and a comparison of the results with those of other methods show the efficiency of the proposed algorithm.http://ijict.itrc.ac.ir/article-1-99-en.htmltext detectiontext localizationimage inpaintingstructural and textural featurescolor segmentation
spellingShingle Mohammad Khodadadi Azadboni
Alireza Behrad
Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
International Journal of Information and Communication Technology Research
text detection
text localization
image inpainting
structural and textural features
color segmentation
title Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
title_full Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
title_fullStr Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
title_full_unstemmed Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
title_short Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features
title_sort text localization extraction and inpainting in color images using combined structural and textural features
topic text detection
text localization
image inpainting
structural and textural features
color segmentation
url http://ijict.itrc.ac.ir/article-1-99-en.html
work_keys_str_mv AT mohammadkhodadadiazadboni textlocalizationextractionandinpaintingincolorimagesusingcombinedstructuralandtexturalfeatures
AT alirezabehrad textlocalizationextractionandinpaintingincolorimagesusingcombinedstructuralandtexturalfeatures