Performance Evaluation of Fractal Feature in Recognition of Postal Codes Using an RBF Neural Network and SVM Classifier

This paper presents a new method for isolated Farsi/Arabic characters and digits recognition. Fractal codes which are determined by a fractal encoding method are used as feature in this system. Fractal image compression is a relatively recent technique based on the representation of an image by a contractive transform for which the fixed point is close to the original image. Each fractal code consists of six parameters such as corresponding domain coordinates for each range block, brightness offset and an affine transformation. We made a comparison between support vector machine (SVM) which is based on statistical learning theory and radial basis function (RBF) neural network classifiers. Experimental results on our database which was gathered from various people with different ages and different educational background indicate that fractal codes are suitable features in the application of zip code recognition. This system achieves recognition rates of 92.71% and 91.33% for digits and characters respectively.