| 摘要 |
Herein disclosed is a character recognition system which comprises a video input device which obtains character video signals by raster scanning characters which exist on a medium; a quantization unit which converts said character video signals into binary code video signals; and a character centerline shaping device which transforms said binary code video signals into character centerline figures which are formed by the character centerlines of said binary code video signals. According to the characteristic feature of the present invention, a temporary memory device temporarily stores said character centerline figures; a feature extract device divides said character centerline figures in said temporary memory device into divided regions with lines which have the original scanning direction or which are at right angles with respect to said original scanning direction, takes out every column of partial centerline figures in said divided regions, said column being at a right angle with respect to said lines, and extracts positions of start points of said partial centerline figures in every divided region, positions of end points of said partial centerline figures in said every divided region, and displacements of said partial centerline figures from said start points to said end points; and a sequential logic circuit decides the categories of the character based on the order of the outputs of said feature extract device.
|
