A Comparison of Feedforward and Self-Organizing Approaches to the Font Orientation Problem

We consider the problem of determining the orientation of printed text. The problem differs considerably from traditional OCR, and its applications to automatic inspection requires efficient processing and highly accurate results. Two methods are described. The first is a feedback network, with structure and parameters derived using optimal detection theory. The second method makes use of the LVQ self-organizing networks of T. Kohonen. Experimental results and a complete implementation are described. Both techniques are found to be successful and their relative advantages are discussed.