"A Novel Two-Stage Approach for Translation, Rotation and Scale Invariant Character Recognition"

Abstract

In this paper a method for character recognition, invariant under translation, rotation, and scaling, is addressed. The first step of the method (preprocessing) takes into account the invariant properties of the character using the axis of symmetry and a novel coding that extracts features from the character. The second step (recognition) is achieved by an Artificial Neural Network which is created by Random Weight based Cascade Correlation algorithm (RWCC), in which vectors obtained in the preprocessing step are used as inputs to it. The algorithm is tested in character recognition, using the 26 upper case letters of the alphabet. Only four different orientations and one size (for each letter) were used for training. Recognition was tested with 9 different sizes and a minimum of 36 rotations. The results are encouraging, since it achieved 98% correct recognition. Tolerance to boundary deformations and random noise was tested.