AUTHORS: Noppakun Boonsim
Download as PDF
ABSTRACT: Racing bib number localization in marathon natural images is challenging because in those images, there are many texts appearing in the scene that will produce many false positive texts. This research presents a method to detect racing bib numbers on complex backgrounds based on edge detection technique. The algorithm initially extracts candidate texts by applied vertical edge detection and morphological operations. Then, face detection technique is applied for the verification step. The experiments were tested on over 400 marathon images. It was reported satisfactory by the performance that was improved from the original work.
KEYWORDS: - Racing bib number, Localization, Complex background
REFERENCES:
[1] Ben-Ami, I., Basha, T. and Avidan, S. Racing Bib Numbers Recognition. The British Machine Vision Conference (BMVC); 2012, pp.1–10.
[2] Shivakumara, P., Raghavendra, R., Qin, L., Raja, K.B., Lu, T. and Pal, U. A new multimodal approach to bib number/text detection and recognition in Marathon images. Pattern Recognition 2017, Vol.61, pp. 479–491.
[3] Roy, S., Shivakumara, P., Mondal, P., Raghavendra, R., Pal, U. and Lu, T. A New Multi-modal Technique for Bib Number/Text Detection in Natural Images. Proceedings of Pacific Rim Conference on Multimedia; 2015, pp. 483-494.
[4] Ye, Q. and Doermann, D. Text detection and recognition in imagery. A survey. IEEE transactions on pattern analysis and machine intelligence 2015, Vol.37, No.7, pp.1480–1500.
[5] Epshtein, B., Ofek, E. and Wexler, Y. Detecting text in natural scenes with stroke width transform. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2010.
[6] Howe, N.R. Document binarization with automatic parameter tuning. International Journal on Document Analysis and Recognition 2013, Vol. 16, No. 3, pp.247-258.
[7] Smith, R. An overview of the Tesseract OCR engine. In Document Analysis and Recognition, 2007. ICDAR 2007. Proceeding of the Ninth IEEE International Conference on Document Analysis and Recognition, 2007, pp. 629-633.
[8] Deb, K., Chae, H.U. and Jo, K.H. Vehicle License Plate Detection Method Based on Sliding Concentric Windows and Histogram. JCP 2009, Vol.4, No.8, pp. 771–777.
[9] Du, S., Ibrahim, M., Shehata, M. and Badawy, W. Automatic license plate recognition (ALPR): A state-of-the-art review. IEEE Transactions on circuits and systems for video technology 2013, Vol.23, No.2, pp. 311–325.
[10] Júnior, P.R.M., Neves, J.M., Tavares, A.I. and Menotti, D. Towards an automatic vehicle access control system: License plate location. In Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference, pp. 2916-2921.
[11] Otsu, N. A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics 1979, Vol.9, No.1, pp. 62–66.
[12] Viola, P. and Jones, M. Rapid object detection using a boosted cascade of simple features. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2001.
[13] Zuiderveld, K. Contrast limited adaptive histogram equalization. Graphics gems IV, Academic Press Professional 1994, pp. 474-485.
[14] Benchmark for Enhancing the Standard for Thai language Processing 2016
[Internet]. 2017
[cited 2017 Jun 1]. Available from: https://thailang.nectec.or.th/best/
