Analysis and Synthesis of Deformed Patterns Based on Structural Models

摘要

The combination of analysis and synthesis is a powerful method in tackling complex problems such as handwriting recognition. Some methods have been proposed for synthesis of deformed patterns for handwritten characters. However, existing methods have some limitations that (1) specification of a number of standard, initial shapes is required for synthesis of various patterns, or (2) shapes with complex curve structures cannot be handled. On the other hand, for coping with complex deformations of handwritten characters, the integration of structural descriptions and geometrical/statistical informations has been shown to be powerful in shape description and matching. Applying this idea to pattern synthesis, we present an algorithm for synthesis of deformed patterns by combining structural descriptions of shapes and curve generation techniques. Based on the shape model (class descriptions) in terms of the high-level features integrating several types of information, we can synthesize various patterns incorporating structural, statistical, and geometrical deformations without resorting to some primitive techniques in image transformation or specifying standard, initial patterns. We present some examples and experimental results of pattern synthesis, showing results of handwritten digit recognition using synthetic patterns and comparing the results with recognition of real data.