IEEE Transactions on Pattern Analysis and Machine Intelligence
Text/Graphics Separation Revisited
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
Tahuti: a geometrical sketch recognition system for UML class diagrams
ACM SIGGRAPH 2006 Courses
Distance measures for image segmentation evaluation
EURASIP Journal on Applied Signal Processing
Recognition, Understanding and Aestheticization of Freehand Drawing Flowcharts
ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
Region-Based Hierarchical Image Matching
International Journal of Computer Vision
PaleoSketch: accurate primitive sketch recognition and beautification
Proceedings of the 13th international conference on Intelligent user interfaces
Watershed Cuts: Minimum Spanning Forests and the Drop of Water Principle
IEEE Transactions on Pattern Analysis and Machine Intelligence
LADDER, a sketching language for user interface developers
Computers and Graphics
Morphological operators for flooding, leveling and filtering images using graphs
GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
SSP: sketching slide presentations, a syntactic approach
GREC'09 Proceedings of the 8th international conference on Graphics recognition: achievements, challenges, and evolution
Hand-Drawn Symbol Spotting Using Semi-definite Programming Based Sub-graph Matching
ICFHR '10 Proceedings of the 2010 12th International Conference on Frontiers in Handwriting Recognition
Symbol Spotting in Line Drawings through Graph Paths Hashing
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Hi-index | 0.00 |
Sketch maps are an intuitive way to display and communicate geographic data and an automatic processing is of great benefit for human-computer interaction. This paper presents a method for segmentation of sketch map objects as part of the sketch map understanding process. We use region-based segmentation that is robust to gaps in the drawing and can even handle open-ended streets. To evaluate this approach, we manually generated a ground truth for 20 maps and conducted a preliminary quantitative performance study.