Scribd
Upload
53 views

Text Detection in Natural Scene Images Using Ocr Algorithm

The document proposes using an Optical Character Recognition (OCR) algorithm for text detection in natural scene images. It describes existing approaches like the Pruning, Single-Link Clustering, and Self-Training Distance Metric Learning algorithms and their issues. The proposed method applies OCR to extract only text regions from images for applications like sign board and number plate recognition. A block diagram outlines the steps of the OCR approach which includes detecting regions, edge detection, connected component analysis, and performing OCR on text regions.

Uploaded by

Balachander Rajasekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
53 views

Text Detection in Natural Scene Images Using Ocr Algorithm

The document proposes using an Optical Character Recognition (OCR) algorithm for text detection in natural scene images. It describes existing approaches like the Pruning, Single-Link Clustering, and Self-Training Distance Metric Learning algorithms and their issues. The proposed method applies OCR to extract only text regions from images for applications like sign board and number plate recognition. A block diagram outlines the steps of the OCR approach which includes detecting regions, edge detection, connected component analysis, and performing OCR on text regions.

Uploaded by

Balachander Rajasekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 3

TEXT DETECTION IN NATURAL SCENE IMAGES USING OCR

ALGORITHM
ABSTRACT
Nowadays reading text from the natural scene images is an challenging problem
that has received a significant amount of attention. Text detection in natural scene
images mainly concentrate on the topic of content-based image analysis. Previous
work based on the Pruning algorithm, Single-Link Clustering algorithm and SelfTraining Distance Metric Learning algorithm. Now we present a novel based on
the Optical Character Recognition (OCR) algorithm for text detection in natural
scene images. The OCR algorithm is applied for both sign boards and number plate
recognition. In this method only the text regions are extracted from the natural
scene images.
Major Issues in Existing Work:
Pruning Algorithm:
The technical term for a problem that takes exponential time is intractable
Intractable problems can only be solved for small input sizes

Faster computer speeds will not help muchexponential growth is fast

Single-Link Clustering Alogorithm:


Sensitive to noise and outliers
It produces long, elongated clusters
Self-Training Distance Metric Learning Algorithm:
Incommensurate features d Euclidean distance not meaningful
Side information d Euclidean distance not relevant
Learning distance metrics may thus be desirable

BLOCK DIAGRAM
Input
\
Image

Detect
MSER
Region

Canny
Edge
Detectio
n

Connecte
d
Compone
nt
Analysis

Output
Image

Perform
OCR on
Text
Region

Determi
ne
Boundin
g Box
Region

Stroke
Width
Image

OCR-ADVANTAGE:

Optical character recognition (OCR) is a process of converting a printed document or scanned


page into ASCII characters that a computer can recognise. Computer systems equipped with
such an OCR system improve the speed of input operation, decrease some possible human
errors and enable compact storage, fast retrieval and other file manipulations. The range of
applications include postal code recognition, automatic data entry into large administrative
systems, banking, automatic cartography and reading devices for blind.

APPLICATIONS:
OCR engines have been developed into many kinds of object-oriented OCR applications, such
as receipt OCR, invoice OCR, check OCR, legal billing document OCR.
They can be used for:

Data entry for business documents, e.g. check, passport, invoice, bank statement and
receipt
Automatic number plate recognition
Automatic insurance documents key information extraction
Extracting business card information into a contact list
More quickly make textual versions of printed documents, e.g. book scanning for Project
Gutenberg
Make electronic images of printed documents searchable, e.g. Google Books
Converting handwriting in real time to control a computer (pen computing)
Defeating CAPTCHA anti-bot systems, though these are specifically designed to prevent
OCR
Assistive technology for blind and visually impaired users

You might also like