Vehicle License Plate Recognition Based on Hierarchical Approach

In order to accurately detect the various sizes of vehicle license plates which are included in input image, we introduce hierarchical approach and overlapped partitioning technique in this paper. The proposed approach firstly attempts the license plate detection for entire image. If detection is failed, the image is partitioned into 3 overlapped rectangular areas and the license plate detection is attempted again. If detection is failed again, the image is partitioned into 7 overlapped rectangular areas and license plate detection is attempted. The method to use for detecting license plate in each step is the edge-based projection technique.

[1]  Roberto de Alencar Lotufo,et al.  Automatic number-plate recognition , 1990 .

[2]  A. Çapar,et al.  License Plate Recognition From Still Images and Video Sequences: A Survey , 2008, IEEE Transactions on Intelligent Transportation Systems.

[3]  Bai Hongliang,et al.  A hybrid license plate extraction method based on edge statistics and morphology , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[4]  Wael Badawy,et al.  Automatic License Plate Recognition (ALPR): A State-of-the-Art Review , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Hsi-Jian Lee,et al.  Detection and recognition of license plate characters with different appearances , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[6]  Lin Luo,et al.  An Efficient Method of License Plate Location , 2009, 2009 First International Conference on Information Science and Engineering.

[7]  Krishnan Nallaperumal,et al.  An Efficient Geometric feature based License Plate Localization and Recognition , 2008 .