A novel application of information theory to pattern recognition problems

This paper is concerned with the development of an algorithm for the assessment of information content of 2-D patterns encountered in practical pattern recognition problems. The technique developed is based on the fundamentals of information theory (i.e., the entropy) to assess the translational and rotational information content of patterns which can then be combined to provide for the assessment of the overall information content associated with the particular pattern. The results obtained are then used to derive a practical pattern recogniser for typed character recognition.<
>