A Statistical Approach for Phrase Location and Recognition within a Text Line: An Application to Street Name Recognition
Issue No. 02 - February (2002 vol. 24)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.982898
<p><b>Abstract</b>—In this paper, we describe a new approach to conjointly locate and recognize a street name within a street line. The system developed is based on a probabilistic framework that naturally integrates various knowledge sources to emit a final decision. At the handwriting signal level, hidden Markov models are extensively used to provide the needed matching scores. Several optimization techniques are employed to speed up the processing time. Experiments carried out on large data sets of street line images, automatically extracted from real French mail envelope images, show very promising results.</p>
Phrase detection and recognition, handwriting recognition, statistical modeling, hidden Markov models.
Jean-Michel Bertille, Michel Gilloux, Mounim A. El-Yacoubi, "A Statistical Approach for Phrase Location and Recognition within a Text Line: An Application to Street Name Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 24, no. , pp. 172-188, February 2002, doi:10.1109/34.982898