Despite recent advances in pattern recognition techniques, the field of optical character recognition (OCR) still lags far behind the capabilities of humans. There have been quite a few developments since the last crop of OCR books [1,2,3], in fields such as artificial neural networks and support vector machines. The publication of this volume is therefore timely. It is authored by four “well-known academics who have worked in the field for many years and have made significant and lasting contributions,” as Sargur Srihari put it on the back cover, albeit with significant contributions from postdoctoral fellows, doctoral candidates, and research assistants.

The breadth of coverage is conveyed by the six parts of the book: “Introduction,” “Tools for Image Processing,” “Feature Extraction, Selection, and Creation,” “Pattern Classification Methods,” “Word and String Recognition,” and “Case Studies.” I found the case studies in the final chapter particularly instructive, as they bring together some of the theoretical techniques discussed in earlier chapters.

In the words of Horst Bunke (also from the back cover), “it is a volume the community has been awaiting for a long time, and I can enthusiastically recommend it to everybody working in the area.” I concur and recommend the book to readers interested either in the general field of OCR, or in a more in-depth treatment of the constituent techniques.