Handwritten Character Recognition Using Unique Feature Extraction Technique
This work addresses the problem of improving accuracy in handwritten character recognition for applications in document digitization and automation, but it appears incremental as it combines existing methods without a major breakthrough.
The paper tackled handwritten character recognition by proposing a hybrid feature extraction technique combining geometric, zone-based, and gradient features, and tested it with three neural networks and a Minimum Distance Classifier, finding that the proposed method is more accurate than individual approaches and that Convolutional Neural Networks performed best.
One of the most arduous and captivating domains under image processing is handwritten character recognition. In this paper we have proposed a feature extraction technique which is a combination of unique features of geometric, zone-based hybrid, gradient features extraction approaches and three different neural networks namely the Multilayer Perceptron network using Backpropagation algorithm (MLP BP), the Multilayer Perceptron network using Levenberg-Marquardt algorithm (MLP LM) and the Convolutional neural network (CNN) which have been implemented along with the Minimum Distance Classifier (MDC). The procedures lead to the conclusion that the proposed feature extraction algorithm is more accurate than its individual counterparts and also that Convolutional Neural Network is the most efficient neural network of the three in consideration.