RECOGNITION OF IRREGULARLY SHAPED WORDS BY USING FRACTAL DIMENSION

Abstract

Nowadays, optical character recognition technology is not so advanced as to compete with human perception ability. Parameters such as scene complexity, irregular lighting conditions, skewness, blur and distortion, aspect ratios, perspective impairment, fonts, multilingual environments negatively affect the success of the optical character recognition technology. The aim of this article is to create an algorithm that can resolve irregular words whose characters' scales and rotations are modified. In the algorithm, fractal dimension tool, a fast and stable recognition method, is used. From this viewpoint it is desired to make optical character recognition technology closer to human perception. In order to analyze the algorithm, fractal dimension and image compression data of big, and small alphabetic characters in the tahoma font were recorded in the database. Then, using these characters, irregular word images were obtained. These images, were analyzed by the algorithm built in matlab program and the results were obtained.

Keywords

• Fractal Dimension,Pattern Recognition,Optical Character

References

1. Hamad K.A., Kaya M., A Detailed Analysis of Optical Character Recognition Technology, International Journal of Applied Mathematics, Electronics and Computers, 4 (Special Issue) ( 2016), pp.244-249, ISSN: 2147-82282147.
2. Hamad K.A., Kaya M., A Detailed Analysis of Optical Character Recognition Technology, International Journal of Applied Mathematics, Electronics and Computers, 4 (Special Issue) ( 2016), pp.244-249, ISSN: 2147-82282147.
3. Vamvakas G., Gatos B., Perantonis S.J., Handwritten Character Recognition through Two-Stage Foreground Sub-Sampling, Pattern Recognition, 8 (2010), pp.2807-2816, DOI No: 10.1016/j.patcog.2010.02.018.
4. Yu C.L., Tang Y.Y., Suen C.Y., Document Skew Detection Based on the Fractal and Least Squares Method, Proceedings of 3rd International Conference on Document Analysis and Recognition, Montreal, Quebec, Canada, 1995, Vol. 1, pp. 1149-1152.
5. Moussa S.B., Zahour A.,Benabdelhafid A., Alimi A.M., New Features Using Fractal Multi-Dimensions for Generalized Arabic Font Recognition , Pattern Recognition Letters, 5 ( 2010), pp.361-371, DOI No: 10.1016/j.patrec.2009.10.015.
6. Moussa S.B., Zahour A., Benabdelhafid A., Alimi A.M., Fractal-Based System for Arabic/Latin, Printed/Handwritten Script Identification, 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA, 2008, Vol. 1, pp. 978-981, DOI No: 10.1109/ICPR.2008.4761838.
7. Shivakumara P., Wu L., Lu T., Tan C.L., Blumenstein M., Anami B.S., Fractals Based Multi-Oriented Text Detection System for Recognition in Mobile Video Images , Pattern Recognition, 68 ( 2017), pp.158-174, DOI No: 10.1016/j.patcog.2017.03.018.
8. G. Neil, K. M. Curtis, Shape Recognıtıon Usıng Fractal Geometry, Pattern Recognition, Vol. 30, No. 12 (1997) , pp. 1957-1969.

9. Les T., Kruk M., Osowski S., Objects Classification Using Fractal Dimension And Shape Based On Leaves Classification, ResearchGate, June 2013.
10. D. C. Popescu and H. Yan, Fracatal-Based Method for Colour Image Compression, J. Electronic Imaging ,Vol.4(1) (1995) , pp.23-30.
11. Fractal Dimension- Chapter 2, http://fractalfoundation.org/OFC/OFC-10-1.html [Access February 7, 2018].
12. M. Sonaka, V. Hlavac and R. Boyle, Image Processing, Analysis and Machine Vision, Chapman and Hall Computing, London , 1993.
13. M. Cusenza, Fractal Analysis of the EEG and Clinical Applications, Università Degli Studi Di Trieste, Trieste, Italy, 2012.
14. Buczkowski S., Kyriacos S., Nekka F., Cartilier L., The Modified Box-Counting Method: Analysis of Some Characteristic Parameters, Pattern Recognition, 4 (1998), pp.411-418, DOI No: 10.1016/S0031-3203(97)00054-X