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
Contributor : Hervé Locteau Connect in order to contact the contributor
Submitted on : Monday, November 16, 2009 - 5:14:57 PM
Last modification on : Sunday, June 26, 2022 - 11:50:51 AM
Long-term archiving on: : Thursday, June 17, 2010 - 8:34:31 PM


Publisher files allowed on an open archive



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⟩



Record views


Files downloads