License Plate Localization With Efficient Markov Chain Monte Carlo

This paper presents a novel efficient Markov Chain Monte Carlo (MCMC) method for License Plate (LP) localization. The proposed method formulates the LP image feature and prior knowledge into a unified Bayesian framework. Then the localization problem is derived as a maximizing-a-posterior (MAP) problem, which integrates color, edge and character feature of LP. We propose an efficient MCMC method, taking integrated local geometrical likelihood as proposal probability to make the inference feasible. The experimental results on real dataset are very promising in terms of detection rate and localization accuracy.

[1]  Yu Cao,et al.  2D nonrigid partial shape matching using MCMC and contour subdivision , 2011, CVPR 2011.

[2]  Jianmin Xu,et al.  Method of License Plate Location Based on Corner Feature , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[3]  Yong Haur Tay,et al.  Detection of license plate characters in natural scene with MSER and SIFT unigram classifier , 2010, 2010 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology.

[4]  Qiang Wu,et al.  Learning-Based License Plate Detection Using Global and Local Features , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[5]  Yang Wang,et al.  Feature clustering for vehicle detection and tracking in road traffic surveillance , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[6]  Rong Zhang,et al.  Integrating bottom-up/top-down for object recognition by data driven Markov chain Monte Carlo , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Jean-Marc Odobez,et al.  Text detection, recognition in images and video frames , 2004, Pattern Recognit..

[8]  Thomas S. Huang,et al.  Robust license plate detection using image saliency , 2010, 2010 IEEE International Conference on Image Processing.

[9]  Langis Gagnon,et al.  Unconstrained license plate detection using the Hausdorff distance , 2010, Defense + Commercial Sensing.

[10]  Harm J. W. Belt.  Word length reduction for the integral image , 2008, 2008 15th IEEE International Conference on Image Processing.

[11]  Jin Hyung Kim,et al.  Color Texture-Based Object Detection: An Application to License Plate Localization , 2002, SVM.

[12]  John W. Fisher,et al.  Efficient MCMC sampling with implicit shape representations , 2011, CVPR 2011.

[13]  Usman Ullah Sheikh,et al.  Character-based car plate detection and localization , 2010, 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010).

[14]  Jean-Marc Odobez,et al.  Text Detection and Recognition in Images and Videos Text Detection and Recognition in Images and Videos , 2003 .

[15]  Min Wang,et al.  An adaptive method for Chinese license plate location , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[16]  Fatih Murat Porikli,et al.  Robust License Plate Detection Using Covariance Descriptor in a Neural Network Framework , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[17]  Zhuowen Tu,et al.  Image Segmentation by Data-Driven Markov Chain Monte Carlo , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Jing Sun,et al.  License plate locating algorithm based on multi-feature in color image , 2010, 2010 International Conference on Educational and Information Technology.

[19]  Horst Bischof,et al.  Detecting, Tracking and Recognizing License Plates , 2007, ACCV.

[20]  Ramakant Nevatia,et al.  Segmentation and Tracking of Multiple Humans in Crowded Environments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Jiří Matas,et al.  Unconstrained licence plate and text localization and recognition , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[22]  Frank Dellaert,et al.  MCMC-based particle filtering for tracking a variable number of interacting targets , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.