License plate recognition based on SIFT feature

Abstract Although license plate recognition (LPR) system is widely applied in practice, its some key techniques that cannot meet application requirements in natural scenes still need more attention, such as Chinese character recognition, candidate filtration, tilt correction, and character segmentation. In this paper, a novel method based on SIFT feature is devised to solve the four problems simultaneously. Promising experimental results demonstrate that the proposed is robust to various adverse factors, such as complex background, scaling variation, rather large tilting angle, contamination, illumination variation, partial occlusion, and defective character. The success rates of Chinese character recognition and candidate filtration reaches to 96%; the tilt correction accuracies reach to 0.177° and 0.238° in horizontal and vertical directions respectively; and the success rate of character segmentation approaches 100%. Remarkably, the average execution time for these four processes is lower than 268 ms, which may favor real-time processing.

[1]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[2]  Ioannis Anagnostopoulos,et al.  A License Plate-Recognition Algorithm for Intelligent Transportation System Applications , 2006, IEEE Transactions on Intelligent Transportation Systems.

[3]  Yan Zhou,et al.  Based on Particle Swarm Optimization real-time license plate recognition , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[4]  Ying Zhang,et al.  License plate character recognition algorithm based on filled function method training bp neural network , 2008, 2008 Chinese Control and Decision Conference.

[5]  Qingming Huang,et al.  A configurable method for multi-style license plate recognition , 2009, Pattern Recognit..

[6]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[7]  Yong Haur Tay,et al.  Two-Stage License Plate Detection Using Gentle Adaboost and SIFT-SVM , 2009, 2009 First Asian Conference on Intelligent Information and Database Systems.

[8]  Guoyou Wang,et al.  A Fast Method for Two-stage Precise License Plate Location Based on Fusion of Corner Feature and Gray Level Jumps , 2012, 2012 International Conference on Industrial Control and Electronics Engineering.

[9]  Qi Tian,et al.  Principal Visual Word Discovery for Automatic License Plate Detection , 2012, IEEE Transactions on Image Processing.

[10]  WU Yi-quan.  Slant Correction of Vehicle License Plate Based on Color Pair Principal Component Analysis , 2008 .

[11]  Hiroshi Kawakami,et al.  A novel adaptive morphological approach for degraded character image segmentation , 2005, Pattern Recognit..

[12]  Xinnian Wang,et al.  A Novel Algorithm for Character Segmentation of Degraded License Plate Based on Prior Knowledge , 2007, 2007 IEEE International Conference on Automation and Logistics.

[13]  Haiyan Zhao,et al.  License plate recognition system based on morphology and LS-SVM , 2008, 2008 IEEE International Conference on Granular Computing.

[14]  Fu Xiao-li.  The Method of Detecting and Correcting Oblique License Plate Based on the Corner Points Information and Inertial Principal Axis , 2009 .

[15]  Jing-Ming Guo,et al.  License Plate Localization and Character Segmentation with feedback self-learning and hybrid-binarization techniques , 2008, TENCON 2007 - 2007 IEEE Region 10 Conference.

[16]  Muhammed Cinsdikici,et al.  Automatic number plate information extraction and recognition for intelligent transportation system , 2007 .

[17]  Chao Li,et al.  Real-Time Anti-Interference Location of Vehicle License Plates Using High-Definition Video , 2009, IEEE Intelligent Transportation Systems Magazine.

[18]  Xing Yang,et al.  Self-adaptive model of texture-based target location for intelligent transportation system applications , 2013 .

[19]  Junyu Dong,et al.  A Simple Method for Chinese License Plate Recognition Based on Support Vector Machine , 2006, 2006 International Conference on Communications, Circuits and Systems.