An Overview of Neural OCR Networks

Abstract

Because neural networks specialize in handling ambiguous data, they are especially suited for such applications as speech recognition and optical character recognition (OCR). OCR applications are usually ambiguous because their data is generated by an inconsistent factor—the individual. This article provides an overview of neural networks and describes how this technology can be integrated with OCR technology to create neural OCR networks that can significantly improve the process of optical character recognition.

Additional information

Notes on contributors

Herbert F Schantz

Herbert F. Schantz, an independent consultant and author specializing in automated compound document management systems design, applications, and cost benefits, is president of HLS Associates. He is a director and former vice-president of The Recognition Technology Users Association, and a member of the ANSI Standards Committee of Information Processing (X3). Schantz is a graduate of Drexel University with a BSME and an MS in Management Sciences.