Character Segmentation for License Plate Recognition by K-Means Algorithm
In this paper an improved K-means algorithm is presented to cut character out of the license plate images. Although there are many existing commercial LPR systems, with poor illumination conditions and moving vehicle the accuracy impaired. After examination and comparison of different image segmentation approaches, the K-means algorithm based method gave better image segmentation results. The K-means algorithm was modified by introducing automatic cluster number determination by filtering SIFT key points. After modification it efficiently detects the local maxima that represent different clusters in the image. The process is successful by getting a clean license plate image. While testing by the OCR software, the experimental results show a high accuracy of image segmentation and significantly higher recognition rate. The recognition rate increased from about 86.6% before our proposed process to about 94.03% after all unwanted non-character areas are removed. Hence, the overall recognition accuracy of LPR was improved.
Keywordsimage segmentation LPR K-means algorithm
- 1.Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice Hall, Englewood Cliffs (2002)Google Scholar
- 10.Soundararajan, P., Sarkar, S.: Analysis of Mincut, Average cut, and Normalized Cut Measures. In: Third Workshop Perceptual Organization in Computer Vision (2001)Google Scholar
- 13.Chazelle, B.: Application challenges to computational geometry: CG Impact Task Force Report. Technical Report TR-521-96, Princeton University (1996)Google Scholar
- 18.Wu, C., et al.: A Macao License Plate Recognition System. In: IEEE Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, vol. 7, pp. 4506–4510 (2005)Google Scholar
- 19.Guo, J.M., et al.: License Plate Localization and Character Segmentation with Feedback Self-learning and Hybrid-binarization Techniques. In: IEEE Region 10 Conference, pp. 1–4 (2007)Google Scholar