Optical Character Recognition

As optical character recognition (OCR) begins to find applicationsranging from store checkout scanners to money-changing machines andpostal system automation, it has become one of the most dynamicareas in information science today. Yet few volumes explore thisdata-oriented process without relying heavily on mathematicalbackground reading. Now, Shunji Mori, Hirobumi Nishida, and Hiromitsu Yamada, among thefield's most respected researchers since its inception, presentthis self-contained, clearly written guidebook to OCR--the firstcomprehensive treatment of the preprocessing, feature-extraction,and systematic description-matching stages of the OCR process.Including a wealth of original research material available here forthe first time, this book is both an ideal professional referencesource and an excellent entry point for course work in thesubject. Key features of Optical Character Recognition:* Theoretical framework based on functional analysis--notpreviously available in a detailed, English-language version* Extensive explanation of preprocessing theory, including blurringand sampling, normalization, thinning, and binary and gray-scalemorphology* Intensive section on feature extraction, exploring linearmethods, structure analysis, and algebraic description* Original work on systematic shape description as a prerequisiteto matching* Original material on elastic matching, including imagerecognition of characters and objects* Requires only the standard undergraduate requisites of algebra,linear algebra, and advanced calculus