An Automatic Number Plate Recognition of Bangladeshi Vehicles

a-day, the importance of automatic traffic monitoring has drawn the attention to the intelligent transport systems. A number plate is the unique identification of a vehicle. Automatic Number Plate Recognition (ANPR) is designed to locate and recognize the number plate of a moving vehicle automatically. For Bangladeshi Vehicles there are no fixed rules for number plates like other countries. Because of the variety of conditions and patterns, the recognition process of number plates for Bangladeshi vehicles is so difficult. We develop a ANPR system which is divided into three part such as number plate Localization, Extraction and Recognition. After successfully complete localization and extraction of number plate we send that portion to a Bangla OCR to fetch the text of the number plate for further processing. In this paper we present a complete ANPR system for Bangladesh Vehicles using standard algorithms with some customization and with our own algorithm for Number Plate extraction which can detect Number Plate region and successfully extract detected region and then able to recognize that number plate text. KeywordsSobel Operator; Outsu threshold; Hough transform; Bangladeshi vehicles number plate

[1]  Remus Brad,et al.  License Plate Recognition System , 2002 .

[2]  A. Govardhan,et al.  Statistical Analysis for Performance Evaluation of Image Segmentation Quality Using Edge Detection Algorithms , 2011 .

[3]  Md. Abu Naser Bikas,et al.  A Complete Workflow for Development of Bangla OCR , 2012, ArXiv.

[4]  Ye Zhang,et al.  Mathematical Morphology Methodology for Extraction of Vehicle Number Plates , 2008 .

[5]  M. Sarfraz,et al.  License plate recognition system , 2003, 10th IEEE International Conference on Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003.

[6]  M. Shadab Mashuk,et al.  Automatic Detection of Bangla Characters in Bangladeshi Car Registration Plates , 2010, 2010 Second International Conference on Computational Intelligence, Modelling and Simulation.

[7]  E.D. Di Claudio,et al.  Car plate recognition by neural networks and image processing , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[8]  Majid Mirmehdi,et al.  Finding Text Regions Using Localised Measures , 2000 .

[9]  Duong Anh Duc,et al.  Combining Hough transform and contour algorithm for detecting vehicles' license-plates , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[10]  Changping Liu,et al.  A hybrid License Plate Extraction Method Based On Edge Statistics and Morphology , 2004, ICPR.

[11]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[13]  Richard O. Duda,et al.  USE OF THE HOUGH TRASFORMTION TO DETECT LINES AND CURVES IN PICTURES Technical Note 36 April 1971 By : , 2006 .

[14]  Majid Mirmehdi,et al.  Combining statistical measures to find image text regions , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[15]  Xiangjian He,et al.  Mean shift for accurate number plate detection , 2005, Third International Conference on Information Technology and Applications (ICITA'05).