Feature extraction of handwritten numeric characters and recognition using an artificial neural network: a new approach

Abstract

Character recognition has been an active area of research and, due to its diverse applicable environment, it continues to be a challenging research topic. The data entry form is a convenient and successful tool for collection of information by filling the sheets with handwritten characters. For many purposes, such as documenting and archiving, extracting the handwritten characters is important. One of the most important fields in these forms is the data-filled boxes. The extraction process is important in processes of handwritten recognition techniques. Feature extraction plays an important role in different classification-based problems, such as face recognition, signature verification, optical character recognition (OCR), etc. The performance of OCR highly depends on the proper selection and extraction of a feature set. Different feature extraction methods are designed for different representations of the characters. The holistic approach is focused on feature extraction of the entire image and recognition using a neural network. This work proposes a subspace approach that regularizes and extracts Eigen features from handwritten numerals. Extracted Eigen features are recognized using a neural network. The proposed algorithm has been successfully implemented and has the added advantage of obtaining the extraction and recognition result at the same time.