This paper investigates the use of both typed and handwritten queries to retrieve handwritten documents. The recognition-based approach reported here is novel in that it expands documents in a fashion analogous to query expansion: Individual documents are expanded using N-best lists which embody additional statistical information from a hidden Markov model (HMM) based handwriting recognizer used to transcribe each of the handwritten documents. This additional information enables the retrieval methods to be robust to machine transcription errors, retrieving documents which otherwise would be unretrievable. Cross-writer experiments on a database of 10985 words in 108 documents from 108 writers, and within-writer experiments in a probabilistic framework, on a database of 537724 words in 3342 documents from 43 writers, indicate that significant improvements in retrieval performance can be achieved. The second database is the largest database of on-line handwritten documents known to its.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Handwritten document retrieval


    Contributors:
    Russell, G. (author) / Perrone, M.P. (author) / Yi-min Chee, (author) / Airnan Ziq, (author)


    Publication date :

    2002-01-01


    Size :

    317122 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Handwritten Document Retrieval

    Russell, G. / Perrone, M. P. / Chee, Y. et al. | British Library Conference Proceedings | 2002



    Transcript Mapping for Historic Handwritten Document Images

    Tomai, C. I. / Zhang, B. / Govindaraju, V. | British Library Conference Proceedings | 2002


    Transcript mapping for historic handwritten document images

    Tomai, C.I. / Bin Zhang, / Govindaraju, V. | IEEE | 2002


    Indexing and retrieval of on-line handwritten documents

    Jain, A.K. / Namboodiri, A.M. | IEEE | 2003