A Fast Binary Template Matching Algorithm for Document Image Data Cmpression.
Murray J. J. Holt · Pattern Recognition · 1988
In the coding of digital facsimile documents, a number of non-information-preserving codes have been proposed which make use of the repetition of binary patterns corresponding to printed or typewritten text characters. The success of such a scheme depends on the accuracy and speed of the template-matching algoritnm which decides whether one pattern may be substituted for another without loss of context or legibility. This paper proposes a template-matching algorithm whose accuracy compares favourably with that of other reported algorithms, and whose execution time is significantly faster in computer simulations. The proposed algorithm is particularly well suited to realisation in parallel hardware.