Classification of digitized documents applying neural networks

Abstract

The exponential increase of the information available in digital format during the last years and the expectations of future growth make it necessary for the organization of information in order to improve the search and access to relevant data. For this reason, it is important to research and implement an automatic text classification system that allows the organization of documents according to their corresponding category by using neural networks with supervised learning. In such a way, a faster process can be carried out in a timely and cost-efficient way. The criteria for classifying documents are based on the defined categories.