Empirical study on neural network based predictive techniques for automatic number plate recognition

M. S. Shashidhara; S. S. Indrakumar

doi:10.1117/12.913485

30 September 2011 Empirical study on neural network based predictive techniques for automatic number plate recognition

M. S. Shashidhara, S. S. Indrakumar

Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 828525 (2011) https://doi.org/10.1117/12.913485
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt

Abstract

The objective of this study is to provide an easy, accurate and effective technology for the Bangalore city traffic control. This is based on the techniques of image processing and laser beam technology. The core concept chosen here is an image processing technology by the method of automatic number plate recognition system. First number plate is recognized if any vehicle breaks the traffic rules in the signals. The number is fetched from the database of the RTO office by the process of automatic database fetching. Next this sends the notice and penalty related information to the vehicle owner email-id and an SMS sent to vehicle owner. In this paper, we use of cameras with zooming options & laser beams to get accurate pictures further applied image processing techniques such as Edge detection to understand the vehicle, Identifying the location of the number plate, Identifying the number plate for further use, Plain plate number, Number plate with additional information, Number plates in the different fonts. Accessing the database of the vehicle registration office to identify the name and address and other information of the vehicle number. The updates to be made to the database for the recording of the violation and penalty issues. A feed forward artificial neural network is used for OCR. This procedure is particularly important for glyphs that are visually similar such as '8' and '9' and results in training sets of between 25,000 and 40,000 training samples. Over training of the neural network is prevented by Bayesian regularization. The neural network output value is set to 0.05 when the input is not desired glyph, and 0.95 for correct input.

Citation Download Citation

M. S. Shashidhara and S. S. Indrakumar "Empirical study on neural network based predictive techniques for automatic number plate recognition", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 828525 (30 September 2011); https://doi.org/10.1117/12.913485

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image processing

Neural networks

Cameras

Databases

Optical character recognition

Image segmentation

Image enhancement

Show All Keywords

Keywords/Phrases

Search In:

Publication Years