Using a Convolutional Neural Network for Machine Written Character Recognition

Convolutional neural networks are special types of artificial neural networks that can solve various tasks in computer vision, such as image classification, object detection, and general recognition. Convolutional neural networks explicitly assume that their inputs are images (2D data), and during their training, they learn how to extract features and classify objects. The paper presents the basic building blocks of convolutional neural networks and their architecture and compares them with other character recognition techniques using the example of character recognition from vehicle registration plates.