The present work is concerned with handwritten and printed numeral recognition based on an improved version of the loci characteristic method (CL) for extracting the numeral features. After a preprocessing of the numeral image, the method divides the image into four equal parts and applies the traditional CL to each of the parts. The recognition rate obtained by this method is improved indicating that the numeral features extracted contain more details. Numeral recognition is carried out in this work through k nearest neighbors and multilayer perceptron techniques.

This paper proposes a new approach of features extraction based on structural and statistical techniques for handwritten, printed and isolated numeral recognition. The structural technique is inspired from the Freeman code, it consists first of contour detection and closing it by morphological operators. After that, the Freeman code was applied by extending its directions to 24-connectivity instead of 8-connectivity. Then, this technique is combined with the statistical method profile projection to determine the attribute vector of the particular numeral. Numeral recognition is carried out in this work through k-nearest neighbors and fuzzy min-max classification. The recognition rate obtained by the proposed system is improved indicating that the numeral extracted features contain more details.

The present paper proposes a new approach of preprocessing for handwritten, printed and isolated numeral characters. The new approach reduces the size of the input image of each numeral by discarding the redundant information. This method reduces also the number of features of the attribute vector provided by the extraction features method. Numeral recognition is carried out in this work through k nearest neighbors and multilayer perceptron techniques. The simulations have obtained a good rate of recognition in fewer running time. General Terms Pattern Recognition, image processing, feature extraction, neural network. Keywords Handwritten and printed numeral recognition, preprocessing, profile projection, k nearest neighbors, multilayer perceptron.

Handwriting, printed character recognition is an interesting area in image processing and pattern recognition. It consists of a number of phases which are preprocessing, feature extraction and classification. The phase of feature extraction is carried out by different techniques; zoning, profile projection, and ameliored Freeman. The high number of features vector can increase the error rate and the training time. So, to solve this problem, we present in this paper a new method of selecting attributes based on the evolution strategy in order to reduce the feature vector dimension and to improve the recognition rate. The proposed model has been applied to recognize numerals and it obtained a better results and showed more robustness than without the selection system.

No abstract