Self-Learning by Word Localization from Images

Intelligence is an interdisciplinary research area which aims at making the machines more human. Extensive research is going on to teach them to perform the tasks. Deep learning is a collection of algorithms in Machine Learning. In this paper we implement deep learning for learning and gaining the knowledge of the text from real time images. An algorithm namely word localization is proposed to able to make the machine to understand the words extracted from the images. In comparison with traditional Optical character recognition (OCR) it has many advantages over it which is been analyzed.