4 February 2013 Semi-structured document image matching and recognition
Author Affiliations +
This article presents a method to recognize and to localize semi-structured documents such as ID cards, tickets, invoices, etc. Standard object recognition methods based on interest points work well on natural images but fail on document images because of repetitive patterns like text. In this article, we propose an adaptation of object recognition for image documents. The advantages of our method is that it does not use character recognition or segmentation and it is robust to rotation, scale, illumination, blur, noise and local distortions. Furthermore, tests show that an average precision of 97.2% and recall of 94.6% is obtained for matching 7 different kinds of documents in a database of 2155 documents.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Olivier Augereau, Olivier Augereau, Nicholas Journet, Nicholas Journet, Jean-Philippe Domenger, Jean-Philippe Domenger, "Semi-structured document image matching and recognition", Proc. SPIE 8658, Document Recognition and Retrieval XX, 865804 (4 February 2013); doi: 10.1117/12.2003911; https://doi.org/10.1117/12.2003911


Knowledge Based Vision For Terrestrial Robots
Proceedings of SPIE (January 04 1989)
Object recognition and matching for image retrieval
Proceedings of SPIE (July 30 2002)
High-volume workflow management in the ITN/FBI system
Proceedings of SPIE (February 06 1997)
Approach to query-by-texture in image database systems
Proceedings of SPIE (November 20 1995)

Back to Top