Recognition of Similar Patterns by Mutilayer Nets and Detection of Rotated Angle and Scale Ratio

For practical pattern recognition, it is required not only to recognize geometrically similar patterns but also to detect the difference of translation, rotation and size from their templates. This paper proposes a method to recognize the simiar patterns by a mutilayer net and then detect the difference on the common basis of well-known geometrical characteristics (center of gravity, angle of principal axis, and variance). It is found from experimental resuts that, with the proposed method, a small net can cassify the similar patterns at a high recognition rate and detect their rotated angles and scale ratios with a high accuracy.