OCR

• Efficient Training of Backpropagation Neural Networks

This paper focuses on gradient-based backpropagation algorithms that use either a common adaptive learning rate for all weights or a separate adaptive learning rate for each weight. The learning-rate adaptation is based on descent techniques and estimates of the local constants that are obtained without additional error function and gradient evaluations. This paper proposes three algorithms to improve the different versions of backpropagation training in terms of both convergence rate and convergence characteristics, such as stable learning and robustness to oscillations. The new modification consists of a simple change in the error signal function. Experiments are conducted to compare and evaluate the convergence behavior of these gradient-based training algorithms with three training ...

• Neural Network World; International Journal on Neural and Mass - Parallel Computing and Information Systems
• Band 16 Nr. 4, Juli 2006

• Optical Character Recognition Motivated by Primate Visual System

A visual nervous system inspired approach to optical character recognition is proposed in this paper with the hope to touch human performance in a limited extent. Particularly, the application of features motivated by the hierarchical structure of the visual ventral stream for recognition of both English and Persian handwritten digits is investigated. Features are derived by combining position and scale invariant edge detectors in a hierarchy over neighboring positions and multiple orientations. The extracted features are then used to train and test a classifier. We examine three types of classifiers: ANN, SVM and kNN to show that features are not dependent on a specific classifier which is in support of these features. The evaluation of the proposed method over standard Persian and Eng...

• Neural Network World; International Journal on Neural and Mass - Parallel Computing and Information Systems
• Band 17 Nr. 5, September 2007

• A Segmentation Method to Handwritten Word Recognition

This paper presents a segmentation technique to handwritten word recognition. This technique implements an algorithm based on an analytical approach. It uses a letter sweeping procedure with a step equal to the Euclidean distance between an established reference index and the entity (the alphabet letter). Then a dissociation of this entity is achieved when this distance will reach a rate of 80%. Our experience about this segmentation technique gives a rate of 81.05% of recognition. A neural multilayer perceptron classifier confirms the extracted segment. This procedure is successively repeated from the beginning until the end of the word. A concatenation technique is finally used to the word reconstitution.

• Neural Network World; International Journal on Neural and Mass - Parallel Computing and Information Systems
• Band 17 Nr. 3, Mai 2007