Semi-structured document image matching and recognition

Olivier Augereau (1) , Nicholas Journet (1) , Jean-Philippe Domenger (1)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique

This article presents a method to recognize and to localize semi-structured documents such as ID cards, tickets, invoices, etc. 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 di erent kinds of documents in a database of 2155 documents.

Mots clés: document image matching; interest points selection; geometric transformation estimation; document image retrieval

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Traitement du texte et du document

Olivier Augereau, Nicholas Journet, Jean-Philippe Domenger. Semi-structured document image matching and recognition. Document Recognition and Retrieval, Feb 2013, San Fransisco, United States. pp.1-12. ⟨hal-00755748⟩