How to compose a complex document recognition system

Authors:
Hiromichi Fujisawa
Affiliations:
Central Research Laboratory, Hitachi, Ltd., Kokubunji, Tokyo, Japan
Venue:
Proceedings of the 2006 international workshop on Research issues in digital libraries
Year:
2006

Citing 6
Cited 0

Decision Combination in Multiple Classifier Systems

IEEE Transactions on Pattern Analysis and Machine Intelligence
Off-Line, Handwritten Numeral Recognition by Perturbation Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lexicon-driven word recognition

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Address-Block Extraction by Bayesian Rule

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02

Quantified Score

Hi-index	0.01

Visualization

Abstract

The technical challenges in document analysis and recognition have been to solve the problems of uncertainty and variability. From our experiences in developing OCRs, business form readers, and postal address recognition engines, we would like to present design principles to cope with these problems of uncertainty and variability. When the targets of document recognition are complex and diversified, the recognition engine needs to solve many different kinds of pattern recognition problems, which are a reflection of uncertainty and variability. Inevitably, the engine becomes complex, raising a question of how to combine its subcomponents, which are not perfect in their accuracies. The design principles will be explained with examples in postal address recognition.