TITLE GTU ID: 22222

PREPARED BY: STUDENT NAME, GUIDED BY: GUIDE NAME

Enrollment No.:- ASSISTANT PROFESSOR,
Sigma Institute of Engineering, Vadodara Sigma Institute of Engineering, Vadodara

ABSTRACT PROPOSED SYSTEM

Text or character detection in a natural scene is an important part of many
Computer Vision tasks. As like, the operation of (OCR) optical character recognition
algorithms can be highly improved by first finding the regions of text or character in
the image. Text detection in natural images, in stand of scans of printed pages,
faxes and business cards, is an important step for a number of Computer Vision
applications. Text detection in natural scenes is a highly researched field, and there
are numerous approaches for solving this problem[1]. Text or character Detection in
Natural Scenes with Stroke Width Transform is a process to detect a text or a
character from natural image using SWT (Stroke Width Transform). The Stroke
Width Transform is a local image operator which computes per pixel the width of the
most likely stroke containing the pixel[2]. SWT is an elegant approach to detect text.
In natural images it is much harder, because there is far less text, and there exists
less overall structure with high variability both in geometry and appearance
compare to scanned text.

INTRODUCTION SYSTEM DESIGN

Text or character detection in a natural scene is an important part of many
Computer Vision tasks. As like, the operation of (OCR) optical character recognition
algorithms can be highly improved by first finding the regions of text or character in
the image. Text detection in natural images, in stand of scans of printed pages,
faxes and business cards, is an important step for a number of Computer Vision
applications. Text detection in natural scenes is a highly researched field, and there
are numerous approaches for solving this problem[1]. Text or character Detection in
Natural Scenes with Stroke Width Transform is a process to detect a text or a
character from natural image using SWT (Stroke Width Transform). The Stroke
Width Transform is a local image operator which computes per pixel the width of the
most likely stroke containing the pixel[2]. SWT is an elegant approach to detect text.
In natural images it is much harder, because there is far less text, and there exists
less overall structure with high variability both in geometry and appearance
compare to scanned text.

OBJECTIVE
 To implement and improve the algorithm so most of the text in a natural image
will be discovered and to reduce noise as possible.
 To identify curvy letters better, such as Gujarati Fonts, Arabic fonts or cursive
handwriting.

WEAKNESS OF CURRENT SYSTEM CONCLUSION

Text or character detection in a natural scene is an important part of many
Computer Vision tasks. As like, the operation of (OCR) optical character recognition
algorithms can be highly improved by first finding the regions of text or character in
the image. Text detection in natural images, in stand of scans of printed pages,
faxes and business cards, is an important step for a number of Computer Vision
applications. Text detection in natural scenes is a highly researched field, and there
are numerous approaches for solving this problem[1]. Text or character Detection in
Natural Scenes with Stroke Width Transform is a process to detect a
In this present work it has been concluded that Detecting Text or character in Natural
Scenes with Stroke Width Transform allows us to apply the method to many fonts and
languages. The grouping of letters can be improved by considering the directions of the
recovered strokes. Using the hybrid approach curvy character and hand written letters
can be detected.

TOOLS & TECHNOLOGY REFERENCES

[1] Gili Werner.”Text Detection in Natural Scenes with Stroke Width Transform”.ICBV,
2013.
[2] B. Epshtein, E. Ofek, and Y. Wexler, “Detecting text in natural scenes with stroke
width transform,” in Computer Vision and Pattern Recognition (CVPR), 2010 IEEE
Conference on. IEEE, 2010, pp. 2963–2970.

SIE TECHEXPO 2019 - A Project Exhibition