Matching of graphical symbols in line-drawing images using angular signature information

Tabbone, Salvatore; Wendling, Laurent; Tombre, Karl

doi:10.1007/s10032-003-0105-0

Cited by 42 publications

(34 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The edges can be labeled or not (if unlabeled the significance is Boolean: we have or have not a relation between two connected components) and can be relations of spatial proximity, based on "forces" [13], orientation or another criterion. In our actual implementation the distance between centers of connected components is used (see Fig.…”

Section: Labeling Connected Componentsmentioning

confidence: 99%

Clustering Document Images Using Graph Summaries

Barbu¹,

Héroux²,

Adam³

et al. 2005

Machine Learning and Data Mining in Pattern Recognition

View full text Add to dashboard Cite

show abstract

Section: Labeling Connected Componentsmentioning

confidence: 99%

Clustering Document Images Using Graph Summaries

Barbu¹,

Héroux²,

Adam³

et al. 2005

Machine Learning and Data Mining in Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Other techniques work with a previous ad-hoc coarse segmentation (Tabbone et al, 2003) between text and graphics, or thick and thin lines to separate symbols from background. Global numerical shape descriptors are then computed at each location and compared against the training set of pixel features extracted from model symbols.…”

Section: Related Workmentioning

confidence: 99%

Relational indexing of vectorial primitives for symbol spotting in line-drawing images

Rusiñol

Borrís

Lladós

2010

Pattern Recognition Letters

View full text Add to dashboard Cite

This paper presents a symbol spotting approach for indexing by content a database of line-drawing images. As line-drawings are digital-born documents designed by vectorial softwares, instead of using a pixel-based approach, we present a spotting method based on vector primitives. Graphical symbols are represented by a set of vectorial primitives which are described by an offthe-shelf shape descriptor. A relational indexing strategy aims to retrieve symbol locations into the target documents by using a combined numerical-relational description of 2D structures. The zones which are likely to contain the queried symbol are validated by a Hough-like voting scheme. In addition, a performance evaluation framework for symbol spotting in graphical documents is proposed. The presented methodology has been evaluated with a benchmarking set of architectural documents achieving good performance results.

show abstract

“…Some techniques work with a previous ad-hoc rough segmentation, as in [22,23], between text and graphics, or thick and thin lines to separate symbols from background. Global numeric shape descriptors are then computed at each location and compared against the training set of pixel features extracted from model symbols.…”

Section: Symbol Spottingmentioning

confidence: 99%