Abstract
This paper describes a recognition algorithm for zip code field recognition. The algorithm consists of an initial character segmentation algorithm and a connected-numeral splitting algorithm. The initial character segmentation algorithm employs connected component analysis with component merge technique based on proximity. The numeral splitting algorithm consists of a slant splitting algorithm based on discriminant analysis and two postprocessing algorithms based on local shape analysis. The splitting algorithm is integrated with a statistical classifier to form a segmentation-recognition algorithm to resolve the ambiguity of connected numeral splitting. The performance is tested by recognition experiments on zip code fields collected from real USPS mail envelopes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fenrich R, Krishnamoorthy K (1990) Segmenting diverse quality handwritten digit strings in near real-time. In: Proceedings of 4th Advanced Technology Conference, pp 523–537
Fukunaga K (1972) Introduction of statistical pattern recognition. Academic, New York and London. p 260
Gillies AM, Gader PD, Whalen MP, Mitchell BT (1989) Application of mathematical morphology to handwritten ZIP code recognition. SPIE vol. 1199 Visual Communications and Image Processing IV, pp 380–389
Hull JJ, Srihari SN, Cohen E, Kuan CL, Cullen P and Palumbo P (1988) A blackboard-based approach to handwritten ZIP code recognition. In: Proceedings of USPS Advanced Technology Conference, pp 1018–1032
Iijima T, Genchi H, Mori K (1973) A theory of character recognition by pattern matching method. Proceedings of First International Conference on Pattern Recognition, pp 50–56
Kimura F, Shridhar M (1991a) Handwritten numeral recognition based on multiple algorithms. Pattern Recognition 24(10):969–983
Kimura F, Shridhar M (1991b) Recognition of connected numeral strings. In: Proceedings of 1st International Conference on Document Analysis and Recognition, Sep. 30–Oct. 2 St.-Malo, France
Mitchell BT and Gillies AM (1988) Advanced research in recognizing handwritten ZIP codes. In: Proceedings of USPS Advanced Technology Conference, pp 813–827
Otsu N (1979) A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions, Systems, Man, and Cybernetics Vol. SMC-9 (1):62–66
Otsu N (1980) An automatic threshold selection method based on discriminant and least squares criteria. IEICE Transactions, vol. J63-D No. 4 pp 349–356
Schurmann J (1978) A multifont word recognition system for postal address reading. IEEE Transactions, Computers, vol. C-27(8):721–732
Shridhar M, Badreldin A (1986) Recognition of isolated and simply connected handwritten numerals. Pattern Recognition 19(1):1–12
Shridhar M, Badreldin A (1987) Context-directed segmentation algorithm for handwritten numeral strings. Image and Vision Computing 5(1):3–9
Srihari SN, Cohen E, Hull JJ and Kuan L (1989) A system to locate and recognize ZIP codes in handwritten addresses. IJRE pp 37–45, Vol 1
Watanabe S, Pakuasa N (1973) Subspace method of pattern recognition. Proceedings of First International Conference on Pattern Recognition, pp 25–32
Watanabe S, Nakamura Y, Suda M, Oh-i K, Yura K, Sasaki H, Takagi N, Tanaka A (1988) Kanji character recognition and its application to address reading. Proceedings of USPS Advanced Technology Conference, pp 828–841
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kimura, F., Shridhar, M. Segmentation-recognition algorithm for zip code field recognition. Machine Vis. Apps. 5, 199–210 (1992). https://doi.org/10.1007/BF02626998
Issue Date:
DOI: https://doi.org/10.1007/BF02626998