Best Combination of Binarization Methods for License Plate Character Segmentation

ETRI Journal

关键词: automatic license plate recognition;    binary image;    binarization;    Character segmentation;   

Others  :  1196680
DOI  :  10.4218/etrij.13.0112.0545

【 摘 要 】

A connected component analysis from a binary image is a popular character segmentation method but occasionally fails to segment the characters owing to image noise and uneven illumination. A multimethod binarization scheme that incorporates two or more binary images is a novel solution, but selection of binarization methods has never been analyzed before. This paper reveals the best combination of binarization methods and parameters and presents an in-depth analysis of the multimethod binarization scheme for better character segmentation. We carry out an extensive quantitative evaluation, which shows a significant improvement over conventional single-method binarization methods. Experiment results of six binarization methods and their combinations with different test images are presented.

   

【 参考文献 】

• [1]C.E. Anagnostopoulos et al., "License Plate Recognition from Still Images and Video Sequences: A Survey," IEEE Trans. Intell. Transp. Syst., vol. 9, no. 3, 2008, pp. 377-391.
• [2]S. Nomura et al., "A Novel Adaptive Morphological Approach for Degraded Character Image Segmentation," Pattern Recog., vol. 38, no. 11, 2005, pp.1961 -1975.
• [3]H.T. Lue et al., "A Novel Character Segmentation Method for Text Images Captured by Cameras," ETRI J., vol. 32, no. 5, Oct. 2010, pp. 729-739.
• [4]Y. Yoon et al., "Blob Extraction Based Character Segmentation Method for Automatic License Plate Recognition System," Proc. IEEE Int. Conf. Syst., Man, Cybern., 2011, pp. 2192-2196.
• [5]J. Sauvola and M. Pietikäinen, ''Adaptive Document Image Binarization,'' Pattern Recog., vol. 33, 2000, pp. 225-236.
• [6]D. Lee and J. Choi, "Precise Detection of Car License Plates by Locating Main Characters," J. Optical Soc. Korea, vol. 14, no. 4, 2010, pp. 376-382.
• [7]Y. Yoon et al., "Blob Detection and Filtering for Character Segmentation of License Plates," Proc. Int. Works. MMSP, 2012, pp. 349-353.
• [8]N. Otsu, "A Threshold Selection Method from Gray Level Histograms," IEEE Trans. Syst., Man, Cybern., vol. 9, no. 1, 1979, pp. 62-66.
• [9]J. Kittler and J. Illingworth, "Minimum Error Thresholding," Pattern Recog., vol. 19, no. 1, Jan./Feb. 1986, pp. 41-47.
• [10]M. Sezgin and B. Sankur, "Survey over Image Thresholding Techniques and Quantitative Performance Evaluation," J. Electron. Imaging, vol. 13, no. 1, 2004, pp. 146-168.
• [11]W. Niblack, An Introduction to Image Processing, Englewood Cliffs, NJ: Prentice-Hall, 1986, pp. 115-116.
• [12]C. Wolf, J.M. Jolion, and F. Chassaing, "Text Localization, Enhancement and Binarization in Multimedia Documents," Proc. ICPR, vol. 2, 2002, pp. 1037-1040.
• [13]J. Bernsen, "Dynamic Thresholding of Gray-Level Images," Proc. ICPR, 1986, pp. 1251-1255.
• [14]Y. Wen et al., "An Algorithm for License Plate Recognition Applied to Intelligent Transportation System," IEEE Trans. Intell. Transportation Syst., vol. 12, no. 3, 2011, pp. 830-845.
• [15]J. He et al., "A Comparison of Binarization Methods for Historical Archive Documents," ICDAR, 2005, pp. 538-542.
• [16]O.D. Trier and A.K. Jain, "Goal-directed Evaluation of Binarization Methods," IEEE Trans. Pattern Anal. Mach. Intell., vol. 17, no. 12, 1995, pp. 1191-1201.