Abstract
We have implemented a prototype document image editor that incorporates principles and algorithms for Perceptual Organization in order to facilitate selection and manipulation of visually salient image objects. Called ScanScribe, the program serves two purposes. First, it offers an illustration of the advantageous use of Gestalt principles of segmentation and grouping of text and line-art found in diagrams. Second, it is a practical tool for modifying existing diagrams and composing new diagrams from mixed source material. ScanScribe’s user interface design and foundational representations are designed to scale to support recognition of domain objects found by structural matching through subgraph correspondence or other techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Mahoney, J., Fromherz, M.: Handling Ambiguity in constraint-based recognition of stick figure sketches. In: Proc. Document Recognition and Retrieval IX, San Jose, California (2002)
Messmer, B.: Efficient graph matching algorithms for preprocessed model graphs. PhD thesis. Bern Univ., Switzerland (1995)
Saund, E.: Finding Perceptually Closed Paths in Sketches and Drawings. IEEE TPAMI 25(4), 475–491 (2003)
Saund, E., Fleet, D., Larner, D., Mahoney, J.: Perceptually-Supported Image Editing of Text and Graphics. In: Proc. ACM UIST, Vancouver, BC, pp. 183–192 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saund, E., Mahoney, J. (2004). ScanScribe: Perceptually Supported Diagram Image Editing. In: Blackwell, A.F., Marriott, K., Shimojima, A. (eds) Diagrammatic Representation and Inference. Diagrams 2004. Lecture Notes in Computer Science(), vol 2980. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25931-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-540-25931-2_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21268-3
Online ISBN: 978-3-540-25931-2
eBook Packages: Springer Book Archive