Any statistical pattern recognition system includes a feature extraction component. For character patterns, several feature families have been tested, such as the Fourier-Wavelet Descriptors. We are proposing here a generalization of this family: the Fourier-Packet Descriptors. We have selected sets of these features and tested them on handwritten digits: the error rate was 1.55% with a polynom...

In this paper we present two algorithms for selecting prototypes from the given training data set. Here, we employ the bootstrap technique to preprocess the data. We compare the proposed algorithms with the condensed nearest-neighbor algorithm which is order dependent and a genetic-algorithm-based prototype selection scheme which is order independent. Algorithms proposed in this paper are found...

Image recognition problems are usually difficult to solve using raw pixel data. To improve the recognition it is often needed some form of feature extraction to represent the data in a feature space. We use the output of a biologically inspired model for visual recognition as a feature space. The output of the model is a binary code which is used to train a linear classifier for recognizing han...

Pattern recognition methods for complex structured objects such as handwritten characters often have to deal with vast search spaces. Developed techniques, despite significant advancement in the last decade, still face some performance barriers. We believe that additional knowledge about the structure of patterns, elicited from humans perceptions, will help improve the recognition’s performance...

In spite of the advances in pattern recognition technology, Handwritten Bangla Character Recognition (HBCR) (such as alpha-numeric and special characters) remains largely unsolved due to the presence of many perplexing characters and excessive cursive in Bangla handwriting. Even the best existing recognizers do not lead to satisfactory performance for practical applications. To improve the perf...

Completely parallel object recognition is NP-complete. Achieving a recognizer with feasible complexity requires a compromise between parallel and sequential processing where a system selectively focuses on parts of a given image, one after another. Successive fixations are generated to sample the image and these samples are processed and abstracted to generate a temporal context in which result...

We describe a method of recognizing handwritten digits by tting generative models that are built from deformable B-splines with Gaussian \ink generators" spaced along the length of the spline. The splines are adjusted using a novel elastic matching procedure based on the Expectation Maximization (EM) algorithm that maximizes the likelihood of the model generating the data. This approach has man...

A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen’s self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as we...

Introduction What is an artificial neural network and how does it work? Artificial neural network have been developed from generalizations of neural biology model, based on the assumptions that (a) information processing occurs at many simple elements called neurons, (b) signals are passed between neurons over connection links, (c) each connection link has an associated weight, which, in a typi...

In the field of Optical Character Recognition (OCR), zoning is used to extract topological information from patterns. In this paper we propose Zone based features for recognition of the mixer of Handwritten and Printed Kannada Digits. A digit image is divided into 64 zones and pixel density is computed for each zone. This procedure is sequentially repeated for entire zone. Finally 64 features a...