Skip to Main content Skip to Navigation
Conference papers

Symbol Detection Using Region Adjacency Graphs and Integer Linear Programming

Abstract : In this paper, we tackle the problem of localizing graphical symbols on complex technical document images by using an original approach to solve the subgraph isophism problem. In the proposed system, document and symbol images are represented by vector-attributed Region Adjacency Graphs (RAG) which are extracted by a segmentation process and feature extractors. Vertices representing regions are labeled with shape descriptors whereas edges are labeled with feature vector representing topological relations between the regions. Then, in order to search the instances of a model graph describing a particular symbol in a large graph corresponding to a whole document, we model the subgraph isomorphism problem as an Integer Linear Program (ILP) which enables to be error-tolerant on vectorial labels. The problem is then solved using a free efficient solver called SYMPHONY. The whole system is evaluated on a set of synthetic documents.
Complete list of metadata

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/inria-00432616
Contributor : Hervé Locteau <>
Submitted on : Monday, November 16, 2009 - 5:14:57 PM
Last modification on : Thursday, July 8, 2021 - 3:47:52 AM
Long-term archiving on: : Thursday, June 17, 2010 - 8:34:31 PM

File

lebodic_icdar09.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Pierre Le Bodic, Hervé Locteau, Sébastien Adam, Pierre Héroux, Yves Lecourtier, et al.. Symbol Detection Using Region Adjacency Graphs and Integer Linear Programming. International Conference on Document Analysis and Recognition, Computer Vision Center, Jul 2009, Barcelona, Spain. 5 p., ⟨10.1109/ICDAR.2009.202⟩. ⟨inria-00432616⟩

Share

Metrics

Record views

754

Files downloads

1328