While current Postal Address Readers have been adapted and fine tuned once and off-line in a central development lab, the concept of next generation readers presented here will contain a built-in learning capability, which can be referred to as continuous learning from letters. This will be performed on different levels of reading and comprehension, enabling the system to adapt itself to slow changes of mail mix and writing conventions.Preconditions of an adaptive reading system are discussed and an outline of such a system is given, which not only keeps track with the slow changes of input, but also optimizes itself to site specific conditions, thus guaranteeing an optimal solution at each site and at any time within life cycle. The system presented here is funded by BMBF (German Federal Ministry of Education and Research) within the projects READ and ADAPTIVE READ.
A n outline of today's state of the art OCRTechnology is given with its most important approaches from single character recognition to h o b tic word recognition and the co-evolution of hardware technology and pattern recognition capabilities is shown. The relation between font design and the design of an omnifont recognition system is illustrated. The economic relevance of todays's OCR technology is discussed. The article concludes with reflections about future trends in the OCR-field such as growing complexity of patterns and knowledge bases an OCR applications. OverviewWriting is one of man's most significant cultural achievements. If you look into the cultural supplements of our newspapers you realize that they don't get tired of celebrating writing as a cuItura1 monument of mankind.Historians even make a distinction between prehistorical time with oral tradition, and historical time with written tradition. Presumably the oldest testimonies of writing are the 6,000 years old Chinese oracle bones bearing information in written symbols.3,000 years ago the Phoenicians were the first people to mark down names and events in writing, inventing our simple alphabet for this purpose. It was not used for symbolizing objects or terms, but to articulate sounds. A stock of about 30 character symbols is basically sufficient for recording in writing all spoken words of any language. Truly a minimalist approach. Ever since all kinds of documents, religious, legal, scientific, economic ones, have been generated and read by man exclusively.It remains reserved for this century, its second half, to be exact, to be able to decipher by means of a machine this type of writing that only humans had been capable to read before. The arrival of the computer made it necessary not only to feed it with information via keyboard, but also to create an immediate access to written documents (predominantly those on paper) which, up to then, had been generated solely for man's use.Today automatic character recognition is a factor which can no longer be neglected in economic practice. OCR-technology is well established e.g. in postal and banking applications world wide reading information written in Arabic numerals and Roman letters. We can assume, in the near future this will also be true for non-Roman character sets, like Chinese characters.Thus OCR-technology not only helps creating an efficient man machine interface but also carries the potential of an important intercultural contribution as man man interface.
No abstract
We provide an overview of the world largest industrial OCR application: Postal Address Reading. We will talk about its humble beginnings and will elaborate how it evolved rapidly to high-tech machinery and discuss its future prospects. Some prominent historical-, system-, methodological-, cultural-and social aspects will also be illuminated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.