Text recognition with artificial neural networks and openCV

Abstract

Recognizing text in images has received attention recently. Traditional systems during this space have relied on elaborating models incorporating rigorously hand-designed options or giant amounts of previous information. This paper proposed by taking a different route and combines the representational power of large, multilayer neural networks together with recent developments in unsupervised feature learning, which allows us to use a standard framework to coach highly accurate character recognizer and text detector modules. The recognition pipeline of scanning, segmenting, and recognition is examined and delineated completely.