Beta
311954

Enhancement Of Text Recognition In Scene Images

Article

Last updated: 28 Dec 2024

Subjects

-

Tags

-

Abstract

 Text detection and recognition in natural scene images has received significant attention in last years. However, it is still
an unsolved problem, due to some difficulties such as some images may have complex background, low contrast, noise,
and /or various orientation styles. Also, the texts in those images can be of different font types and sizes. These
difficulties make the automatic text extraction and recognizing it very difficult. This paper proposes the
implementation of an intelligent system for automatic detection of text from images and explains the system which
extracts and recognizes text in natural scene images by using some text detection algorithms to enhance text recognition. The proposed system implements various algorithms, such as Maximally Stable Extremal Regions (MSER) algorithm to detect the regions in the image, Canny edges algorithm to enhance edge detection and Bounding Box algorithm to detect and segment area of interest. Once the text is extracted from the image, the recognition process is done using Optical Character Recognition (OCR). The proposed system has been evaluated using public datasets (ICDAR2003 and the experimental results have proved the robust performance of the proposed system
 

DOI

10.21608/mjcis.2017.311954

Keywords

Scene Text Detection, Maximally Stable Extremal Regions, Bounding Box, OCR, OCR Spell Checker

Authors

First Name

Moayed

Last Name

Hamad

MiddleName

-

Affiliation

Faculty of computers and information systems , C.S dep. Mansoura University, Egypt

Email

-

City

-

Orcid

-

First Name

Osama

Last Name

Abu-Elnasr

MiddleName

-

Affiliation

Faculty of computers and information systems , C.S dep. Mansoura University, Egypt

Email

-

City

-

Orcid

-

First Name

Sherif

Last Name

Barakat

MiddleName

-

Affiliation

Faculty of computers and information systems , I.S dep. Mansoura University, Egypt

Email

sheiib@mans.edu.eg

City

-

Orcid

-

Volume

13

Article Issue

1

Related Issue

42818

Issue Date

2017-12-01

Receive Date

2023-08-09

Publish Date

2017-12-01

Page Start

19

Page End

26

Print ISSN

2090-1666

Online ISSN

2090-1674

Link

https://mjcis.journals.ekb.eg/article_311954.html

Detail API

https://mjcis.journals.ekb.eg/service?article_code=311954

Order

311,954

Type

Original Research Articles.

Type Code

1,784

Publication Type

Journal

Publication Title

Mansoura Journal for Computer and Information Sciences

Publication Link

https://mjcis.journals.ekb.eg/

MainTitle

Enhancement Of Text Recognition In Scene Images

Details

Type

Article

Created At

28 Dec 2024