Abstract
Recently, handwriting recognition has found many application areas along with technological advances. Handwriting recognition systems can greatly simplify human life by reading tax returns, forwarding mail, reading bank checks, and so on. On the other hand, these systems can reduce the need for human interaction. Therefore, academic and commercial studies of handwriting characters have recently become an important research topic in pattern recognition. In this study, Turkish handwritten letter recognition system from A to Z was developed in C++ environment by using Artificial Neural Networks (ANNs). After the feature data were extracted, handwriting images were presented to the network, the training process of ANN was completed, and different handwriting images were classified with trained ANN. In this study, MLP (Multi-Layered Perceptron: MLP) type ANN and back-propagation learning algorithm were used. The ANN used has 35 inputs and 23 outputs. In the hidden layer, ANNs with different numbers of artificial neural cells (neurons) were evaluated and the most appropriate neural number ANN was selected. As a result, ANN with 24 neurons was selected in the hidden layer and handwriting images was classified with an accuracy rate of 94.90 %.
Highlights
Artificial neural networks are parallel information processing systems developed inspired by the nerve cells of the human brain
Turkish handwritten letter recognition system from A to Z was developed by using image processing, feature extraction and Artificial Neural Networks (ANNs) algorithms in C++ and OpenCV environments
The handwriting images were presented to the network after the feature data was extracted and the training process of ANN was completed and the handwriting images were tried to be classified
Summary
Artificial neural networks are parallel information processing systems developed inspired by the nerve cells of the human brain. Many handwriting recognition systems have been developed in the literature using artificial neural networks One of these studies is the system that recognizes 33 handwritten characters of the Malayalam alphabet made by Alex M. and Das S. He used an artificial neural network with a number of inputs 400, a single hidden layer and a 250-neuron numbers in the hidden layer They trained ANNs with 5000 different handwritten number samples, and he realized a classification with an accuracy rate of 99.32 %. For each handwriting targeted to be classified, 34 samples written in different ways were evaluated and their characteristics were extracted With this feature data and back propagation algorithm, ANNs were trained to recognize different types of handwriting. As a result of this study, 23 Turkish handwriting character is recognized with 94.90 % accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
