Frequent Graph Discovery
In this paper a sequence of steps is applied to a graph representation of line drawings using concepts from data mining. This process finds frequent subgraphs and then association rules between these subgraphs. The distant aim is the automatic discovery of symbols and their relations, which are part...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2005 |
| País: | España |
| Institución: | Universitat Autònoma de Barcelona |
| Repositorio: | Dipòsit Digital de Documents de la UAB |
| Idioma: | inglés |
| OAI Identifier: | oai:ddd.uab.cat:24337 |
| Acceso en línea: | https://ddd.uab.cat/record/24337 https://dx.doi.org/urn:doi:10.5565/rev/elcvia.95 |
| Access Level: | acceso abierto |
| Palabra clave: | Computer Vision Image Analysis Pattern Recognition Graph Mining Line Drawings Association Rules Visió per computadora Anàlisi d'imatge Reconeixement de dissenys Mineria gràfica Dibuix lineal Transmissió directa Regles d'associació Visión por computadora Análisis de imagen Reconocimiento de diseños Minería gráfica Dibujo lineal Transmisión directa Reglas de asociación |
| Sumario: | In this paper a sequence of steps is applied to a graph representation of line drawings using concepts from data mining. This process finds frequent subgraphs and then association rules between these subgraphs. The distant aim is the automatic discovery of symbols and their relations, which are parts of the document model. The main outcome of our work is firstly an algorithm that finds frequent subgraphs in a single graph setting and secondly a modality to find rules and meta-rules between the discovered subgraphs. The searched structures are closed [1] and disjunct subgraphs. One aim of this study is to use the discovered symbols for classification and indexation of document images when a supervised approach is not at hand. The relations found between symbols can be used in segmentation of noisy and occluded document images. The results show that this approach is suitable for patterns, symbols or relation discovery. |
|---|