An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images
This research work plays a significant role in finding information from the scene images to fulfill the demand of real life applications like detection of license plate, navigation of robot and helping the visually impaired persons. Here, a new algorithm has been proposed and applied on the scene im...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-09-01
|
Series: | Journal of King Saud University: Computer and Information Sciences |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157822000349 |
_version_ | 1811188571677130752 |
---|---|
author | Rashedul Islam Md. Rafiqul Islam Kamrul Hasan Talukder |
author_facet | Rashedul Islam Md. Rafiqul Islam Kamrul Hasan Talukder |
author_sort | Rashedul Islam |
collection | DOAJ |
description | This research work plays a significant role in finding information from the scene images to fulfill the demand of real life applications like detection of license plate, navigation of robot and helping the visually impaired persons. Here, a new algorithm has been proposed and applied on the scene images to extract Region of Interest (ROI). All the Bangla words are then separated from a sentence by analyzing and applying the Connected Component (CC) method along with bounding box technology. Another new algorithm has been proposed and applied to apart and bring-out Bangla characters from the Bangla words. This algorithm works by the method of vertical scanning of the images of Bangla words. Finally, the extracted characters are recognized by using the Support Vector Machine (SVM) as a classifier which works with Histogram of Oriented Gradient (HOG) features. There are 500 scene images with variations in colors, writing styles and orientations in our designed database. The proposed algorithm yields the accuracy 92.70% and 93.23% in extraction of ROI and character respectively. In the recognition of Bangla characters (digits, Basic characters, and joined characters), the average accuracy is 99.16%. The recognition accuracy of Bangla characters using Convolutional Neural Network (CNN) is also calculated and the obtained result is 83.52%. |
first_indexed | 2024-04-11T14:21:01Z |
format | Article |
id | doaj.art-45fff59410334cbb98d551edba9f0a5f |
institution | Directory Open Access Journal |
issn | 1319-1578 |
language | English |
last_indexed | 2024-04-11T14:21:01Z |
publishDate | 2022-09-01 |
publisher | Elsevier |
record_format | Article |
series | Journal of King Saud University: Computer and Information Sciences |
spelling | doaj.art-45fff59410334cbb98d551edba9f0a5f2022-12-22T04:19:03ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-09-0134861506164An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene imagesRashedul Islam0Md. Rafiqul Islam1Kamrul Hasan Talukder2Computer Science & Engineering Discipline, Khulna University, Khulna 9208, BangladeshComputer Science & Engineering Discipline, Khulna University, Khulna 9208, BangladeshComputer Science & Engineering Discipline, Khulna University, Khulna 9208, BangladeshThis research work plays a significant role in finding information from the scene images to fulfill the demand of real life applications like detection of license plate, navigation of robot and helping the visually impaired persons. Here, a new algorithm has been proposed and applied on the scene images to extract Region of Interest (ROI). All the Bangla words are then separated from a sentence by analyzing and applying the Connected Component (CC) method along with bounding box technology. Another new algorithm has been proposed and applied to apart and bring-out Bangla characters from the Bangla words. This algorithm works by the method of vertical scanning of the images of Bangla words. Finally, the extracted characters are recognized by using the Support Vector Machine (SVM) as a classifier which works with Histogram of Oriented Gradient (HOG) features. There are 500 scene images with variations in colors, writing styles and orientations in our designed database. The proposed algorithm yields the accuracy 92.70% and 93.23% in extraction of ROI and character respectively. In the recognition of Bangla characters (digits, Basic characters, and joined characters), the average accuracy is 99.16%. The recognition accuracy of Bangla characters using Convolutional Neural Network (CNN) is also calculated and the obtained result is 83.52%.http://www.sciencedirect.com/science/article/pii/S1319157822000349HOGSVMConnected componentVertical projectionFilteringCharacter recognition |
spellingShingle | Rashedul Islam Md. Rafiqul Islam Kamrul Hasan Talukder An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images Journal of King Saud University: Computer and Information Sciences HOG SVM Connected component Vertical projection Filtering Character recognition |
title | An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images |
title_full | An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images |
title_fullStr | An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images |
title_full_unstemmed | An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images |
title_short | An efficient ROI detection algorithm for Bangla text extraction and recognition from natural scene images |
title_sort | efficient roi detection algorithm for bangla text extraction and recognition from natural scene images |
topic | HOG SVM Connected component Vertical projection Filtering Character recognition |
url | http://www.sciencedirect.com/science/article/pii/S1319157822000349 |
work_keys_str_mv | AT rashedulislam anefficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages AT mdrafiqulislam anefficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages AT kamrulhasantalukder anefficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages AT rashedulislam efficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages AT mdrafiqulislam efficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages AT kamrulhasantalukder efficientroidetectionalgorithmforbanglatextextractionandrecognitionfromnaturalsceneimages |