Use of Contextual Constraints in Recognition of Contour-Traced Handprinted Characters

Robert W. Donaldson, Godfried Toussaint

    Research output: Contribution to journalArticle

    Abstract

    A contour-tracing technique described in an earlier paper [9] was used along with monogram, bigram, and trigram contextual constraints to recognize handprinted characters. Error probabilities decreased by factors ranging from two to four over those which resulted when contextual constraints were ignored. A simple technique for searching over only the most probable bigrams and trigrams was used to significantly reduce the computation without reducing the recognition accuracy.

    Original languageEnglish (US)
    Pages (from-to)1096-1099
    Number of pages4
    JournalIEEE Transactions on Computers
    VolumeC-19
    Issue number11
    DOIs
    StatePublished - Jan 1 1970

    Fingerprint

    Error Probability
    Tracing
    Probable
    Character
    Error probability

    Keywords

    • Block decoding
    • character recognition
    • contextual constraints
    • contour analysis
    • handprinted characters
    • limited-data experiments
    • suboptimum classification

    ASJC Scopus subject areas

    • Software
    • Theoretical Computer Science
    • Hardware and Architecture
    • Computational Theory and Mathematics

    Cite this

    Use of Contextual Constraints in Recognition of Contour-Traced Handprinted Characters. / Donaldson, Robert W.; Toussaint, Godfried.

    In: IEEE Transactions on Computers, Vol. C-19, No. 11, 01.01.1970, p. 1096-1099.

    Research output: Contribution to journalArticle

    Donaldson, Robert W. ; Toussaint, Godfried. / Use of Contextual Constraints in Recognition of Contour-Traced Handprinted Characters. In: IEEE Transactions on Computers. 1970 ; Vol. C-19, No. 11. pp. 1096-1099.
    @article{d924825b71a44556a8f1d7a242bfc049,
    title = "Use of Contextual Constraints in Recognition of Contour-Traced Handprinted Characters",
    abstract = "A contour-tracing technique described in an earlier paper [9] was used along with monogram, bigram, and trigram contextual constraints to recognize handprinted characters. Error probabilities decreased by factors ranging from two to four over those which resulted when contextual constraints were ignored. A simple technique for searching over only the most probable bigrams and trigrams was used to significantly reduce the computation without reducing the recognition accuracy.",
    keywords = "Block decoding, character recognition, contextual constraints, contour analysis, handprinted characters, limited-data experiments, suboptimum classification",
    author = "Donaldson, {Robert W.} and Godfried Toussaint",
    year = "1970",
    month = "1",
    day = "1",
    doi = "10.1109/T-C.1970.222839",
    language = "English (US)",
    volume = "C-19",
    pages = "1096--1099",
    journal = "IEEE Transactions on Computers",
    issn = "0018-9340",
    publisher = "IEEE Computer Society",
    number = "11",

    }

    TY - JOUR

    T1 - Use of Contextual Constraints in Recognition of Contour-Traced Handprinted Characters

    AU - Donaldson, Robert W.

    AU - Toussaint, Godfried

    PY - 1970/1/1

    Y1 - 1970/1/1

    N2 - A contour-tracing technique described in an earlier paper [9] was used along with monogram, bigram, and trigram contextual constraints to recognize handprinted characters. Error probabilities decreased by factors ranging from two to four over those which resulted when contextual constraints were ignored. A simple technique for searching over only the most probable bigrams and trigrams was used to significantly reduce the computation without reducing the recognition accuracy.

    AB - A contour-tracing technique described in an earlier paper [9] was used along with monogram, bigram, and trigram contextual constraints to recognize handprinted characters. Error probabilities decreased by factors ranging from two to four over those which resulted when contextual constraints were ignored. A simple technique for searching over only the most probable bigrams and trigrams was used to significantly reduce the computation without reducing the recognition accuracy.

    KW - Block decoding

    KW - character recognition

    KW - contextual constraints

    KW - contour analysis

    KW - handprinted characters

    KW - limited-data experiments

    KW - suboptimum classification

    UR - http://www.scopus.com/inward/record.url?scp=84863408388&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84863408388&partnerID=8YFLogxK

    U2 - 10.1109/T-C.1970.222839

    DO - 10.1109/T-C.1970.222839

    M3 - Article

    VL - C-19

    SP - 1096

    EP - 1099

    JO - IEEE Transactions on Computers

    JF - IEEE Transactions on Computers

    SN - 0018-9340

    IS - 11

    ER -