Arabic License Plate Recognition Based On Hough Transform
Adel A. Sewisy,
Faculty of Computer and Information Sciences,
Assiut University, Assiut, Egypt,
http://www.aun.eun.eg

Abstract:

This paper proposes an automatic license plate recognition (LPR) system for Egyptian license plates. To implement the presented algorithm digital image processing techniques and Hough Transform are employed. The recognition process includes several phases. First, the existence of vehicle was detected. Then the location of plate in the image is recognized and the characters of plate area are extracted by region growing and connectivity algorithms. Information from vertical and horizontal segmentation of the plate is then submitted to Hough transformation, leading to the recognition of all characters set of the plate. The distinguishing features of the plate could then be stored in an appropriate database for future application in tra c aspects. Results of the experiment show good performance with a about 98% rate of success.

Keywords: License plate recognition, Pattern recognition, Image segmentation, Hough Transform

Biography:

Adel Adou Elmagd Sewisy; Assiut; EGYPT; B.Sc. in Mathematics 1984, Assiut University. M.Sc. in Mathematics (Numerical Analysis) 1990, Assiut University. Ph.D. in Computer Science 1997, Assiut University. Demonstrator in Dept. of Math., Faculty of Science, Assiut University 1984. Assistant Lecturer in Dept. of Math., Faculty of Science 1990. Lecturer of Computer Science in Dept. of Math., Faculty of Science 1997. Associate Prof. of Computer Science in Dept. of Computer Science Faculty of Computers and Information Science, Assiut University 2003.Research Interests: Computer Science, Computer Vision, Arti cial Intelligence, Image Processing, Pattern recognition, Computer graphics, Fuzzy logic, Neural Networks, Numerical Analysis, Operation Research

BibTex:

@ARTICLE{P1120650001,

AUTHOR = {Adel A. Sewisy},

TITLE = {Arabic License Plate Recognition Based On Hough Transform},

JOURNAL ={ICGST  International Journal on Artificial Intelligence and Machine Learning, AIML},

}

( Full Paper, 2 MB)