The continuous improvement of general purpose document image processing and recognition techniques over the years has made possible at some points in their history the emergence of successful industrial applications. Among these, postal and check processing applications have been two of the earliest because of their economic significance, stemming from the number of items concerned, and of their particular characteristics that allowed even early document image processing and recognition techniques to produce satisfactory systems. To achieve these results, it has been necessary to integrate contributions from a majority of image processing domains, from image acquisition and preprocessing to interpretation through symbol, character, and word recognition. Through their proved return on investment, these applications have in turn highly driven and contributed to the progress of fundamental recognition techniques in many domains.This chapter reviews their shared and distinctive characteristics, relates their history, and describes their respective state of the art through the components and techniques underlying a typical postal or check recognition system. Finally, it gives pointers to vendors and available image databases and draws some perspectives as to the development of future postal and check recognition systems.
CITATION STYLE
Gilloux, M. (2014). Document analysis in postal applications and check processing. In Handbook of Document Image Processing and Recognition (pp. 705–747). Springer London. https://doi.org/10.1007/978-0-85729-859-1_22
Mendeley helps you to discover research relevant for your work.