This paper describes a global model designed to jointly detect and recognize a street name within a delivery line of an handwritten address block image. The model used is based on Hidden Markov Models (HMM). The lines are firstly preprocessed, then segmented and characterized by two types of features. We create a HMM for each street name by simply concatenating the corresponding letter models, elementary HMM learned on a large city name database. A street name may often be surrounded by other information on the left and on the right within the delivery line. These phenomena are roughly modelled by trigrams. The global model is then simply obtained by the concatenation of trigram models with the HMMs corresponding to street names.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Conjoined location and recognition of street names within a postal address delivery line


    Contributors:


    Publication date :

    1995-01-01


    Size :

    451972 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Conjoined Location and Recognition of Street Names Within a Postal Address Delivery Line

    El Yacoubi, A. / Bertille, J.-M. / Gilloux, M. | British Library Conference Proceedings | 1995


    Postal address block location by contour clustering

    Govindaraju, V. / Tulyakov, S. | IEEE | 2003


    Postal Address Block Location by Contour Clustering

    Tulyakov, S. / Govindaraju, V. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003



    Postal Address Finding and Reading

    Srihari, S. | British Library Online Contents | 1990