Hisashi Saiga

An OCR system for business cards

An experimental business card recognition system is described that recognizes Japanese business cards of a wide variety both in formats and fonts. It also classifies recognition results into several predefined categories so that a business card database is built automatically. The overall procedure divides into a character recognition phase and a linguistic processing phase. In the first phase, the system gives a strictly local approach toward line segmentation to cope with slanted images. In the linguistic processing phase, recognition result strings generated in the former phase are analysed, classified and verified with the help of built databases. Some experimental results are also discussed.<<ETX>>

High-speed recognition of tabulated data

An experimental recognition system for tabular data is described. It recognizes vertical and horizontal lines and, if they form tabular data, it analyzes the tabular structure. The paper proposes a new method to extract dotted lines that allows few, if any, recognition errors. It also describes a new data structure for tabular data that is easily combined with character recognition, which consists of rectangles and their labels. The line and table recognition methods described here is characterized by the fact that it only entails scanning the image array once. Some experimental results are also discussed.