Method for comparing word shapes

A method for determining the relative equivalency or match between two or more character strings represented in an array of image data, including the steps of determining page orientation, isolating (18) character strings from adjacent character strings, and establishing (20,22) a set of boundaries or reference lines about the character strings. Subsequently, the boundaries are used to represent the character string images as word shape contours or signals which are generated (24) from the imaginal data within the boundaries. The word shape contours are then compared (26) using one of the described comparison methods (e.g. Fig. 20) to determine the relative equivalency or similarity of the contours.