Authors: Gary E. Kopec, Phil A Chou

Title:	Document Image Decoding Using Markov Source Models

Where Published: accepted by IEEE Trans. PAMI

Abstract: 

This paper describes a communication theory approach to document image
recognition, patterned after the use of hidden Markov models in speech
recognition.  In general, a document recognition problem is viewed as
consisting of three elements- an image generator, a noisy channel and an
image decoder.  A document image generator is a Markov source (stochastic
finite-state automaton) that combines a message source with an imager. The
message source produces a string of symbols, or text, that contains the
information to be transmitted.  The imager is modeled as a finite-state
transducer that converts the one-dimensional message string into an ideal
two-dimensional bitmap.  The channel transforms the ideal image into a
noisy observed image.  The decoder estimates the message, given the
observed image, by finding the a posteriori most probable path through the
combined source and channel models using a Viterbi-like dynamic programming
algorithm.  The proposed approach is illustrated on the problem of decoding
scanned telephone yellow pages to extract names and numbers from the
listings.  A finite-state model for yellow page columns was constructed and
used to decode a database of scanned column images containing about 1100
individual listings. Overall, 99.5% of the listings were correctly
recognized, with character classification rates of 98% and 99.6%,
respectively, for the names and numbers.


Keywords: document recognition, text recognition, image decoding,
stochastic grammars, Markov models