Making Documents Work: Challenges for Document Understanding
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Information Processing and Management: an International Journal - Special issue: An Asian digital libraries perspective
| Hi-index | 0.00 |
Abstract: This paper describes the ICAR system, an application for automatic reading of identity cards and passports. The system acquires the image of the document by a flatbed scanner and recognizes the type of the document among a set of predefined models using color information. Textual fields are located in the image by a connected component analysis and identified in terms of their structural arrangement. A set of complementary statistical and structural OCR techniques are combined by a voting strategy to read each text image region. For unknown input documents, lines compliant with machine readable ICAO 9303 format are located and recognized. Although the system has been initially designed for Spanish documents, it allows the integration of new formats by a supervised learning procedure. The system is currently installed as a check-in application in a real environment.