Invariant Radon-Moment Descriptor for Postal Applications

• Autorzy: Miciak M.

Identyfikatory

DOI

10.1515/ipc-2015-0040

• Języki publikacji: EN

Abstrakty

EN

In this article a new solution of handwritten digits recognition system for postal applications is presented. Moreover, in this paper, a new approach of handwritten characters recognition was presented. The implemented algorithm is applied to recognition of postal items on the basis of postcode information. In connection with this article the research was carried with all digit characters used in authentic zip code of various mail pieces. Additionally, the paper contains some preliminary image processing for example normalization of the character. The main objective of this article is to use the Radon Transformation and other moments values to obtain an invariant set of character image features, on basis of which postal code will be classified. The reported experiments results prove the effectiveness of the proposed method. Furthermore, causes of errors as well as possible improvement of recognition results will be presented.

Słowa kluczowe

EN

radon transformation; OCR; image normalization

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2015
• Tom: Vol. 20, no. 4
• Strony: 13--21
• Opis fizyczny: Bibliogr. 20 poz., rys.

Twórcy

autor

Miciak M.

• Institute of Telecommunications and Computer Science, Faculty of Telecommunication, Information Technology and Electrical Engineering, University of Technology and Life Sciences (UTP), Kaliskiego 7, 85-789 Bydgoszcz, Poland

Bibliografia

• [1] Aissaoui, A., Haouari, A. (1999). Normalised Fourier coefficients for cursive Arabic script recognition. Applied Signal Processing, 6(3), 115-122
• [2] Andrysiak, T. (2001). Recognition of handwritten characteres using Gabor features, II Krajowa Konferencja Naukowo-Szkoleniowa KOSYR
• [3] Andrysiak, T., ChoraS, M. (2005). Image retrieval based on hierarchical Gabor filters. International Journal of Applied Mathematics and Computer Science, 15(4), 471
• [4] Averbuch, A., Coifman, R.R., Donoho, D.L., Israeli, M., Walden, J. (2001). Fast Slant Stack: A notion of Radon transform for data in a cartesian grid which is rapidly computible, algebraically exact, geometrically faithful and invertible. Department of Statistics, Stanford University
• [5] Bellili, A., Gilloux, M., Gallinari, P. (2003). An MLP-SVM combination architecture for offline handwritten digit recognition. Document Analysis and Recognition, 5(4), 244-252
• [6] Bracewell, R. N., Chang, K. Y., Jha, A. K., Wang, Y. H. (1993). Affine theorem for two-dimensional fourier transform. Electronics Letters, 29(3), 304
• [7] Forella, G. (2000). Word perfect, Postal Technology, UKIP Media & Events Ltd
• [8] Hiriyannaiah, H. P., Ramakrishnan, K. R. (1994). Moments estimation in Radon space. Pattern recognition letters, 15(3), 227-234
• [9] Riggs, R., Holliday, J. (2003). Programming Wireless Devices with the Java 2 Platform: Micro Edition. Addison-Wesley Professional
• [10] Kang, H. I., Lim, S., Kim, K. I., Son, Y. I. (2005, July). A normalization based image affine estimation technique for computer vision. In Advanced Intelligent Mechatronics. Proceedings, 2005 IEEE/ASME International Conference on (pp. 1553-1556). IEEE
• [11] Kaufmann, G., Bunke, H. (2000). Automated reading of cheque amounts. Pattern Analysis & Applications, 3(2), 132-141
• [12] Kupce, E., Freeman, R. (2004). The Radon transform: a new scheme for fast multidimensional NMR. Concepts in Magnetic Resonance Part A, 22(1), 4-11
• [13] Liu, C. L., Sako, H., Fujisawa, H. (2002). Performance evaluation of pattern classifiers for handwritten character recognition. International Journal on Document Analysis and Recognition, 4(3), 191-204
• [14] Hu, M. K. (1962). Visual pattern recognition by moment invariants. information Theory, IRE Transactions on, 8(2), 179-187
• [15] Miciak, M. (2004). The Algorithms of Handwritten Characters Recognition For Postal Application, Signal Processing 2004 Workshop Proceedings, 75-80
• [16] Maszewski, M., Miciak, M. (2007). Character Recognition Based on Fourier Transfrom and CDWT in Postal Applications. In Computer Recognition Systems 2 (pp. 462-469). Springer Berlin Heidelberg
• [17] Miciak, M., Boniecki, R., Marchewka, A. (2010). The Complex System to Postal Code Recognition, Position of Postal Services in Modern Communication Society, 216-221
• [18] Mason, J.C., Handscomb, D.C. (2002). Chebyshev polynomials. CRC Press
• [19] Toft, P. A., Sorensen, J. A. (1996). The Radon transform-theory and implementation (Doctoral dissertation, Technical University of DenmarkDanmarks Tekniske Universitet, Department of Informatics and Mathematical ModelingInstitut for Informatik og Matematisk Modellering)
• [20] Kupce, E., Freeman, R. (2004). The Radon transform: a new scheme for fast multidimensional NMR. Concepts in Magnetic Resonance Part A, 22(1), 4-11