AUTOMATED TUNING OF PARAMETERS FOR THE SEGMENTATION OF FREEHAND SKETCHES

D. G. Fernández-Pacheco, F. Albert, N. Aleixos, J. Conesa, M. Contero

Abstract

One of the main problems in the segmentation of freehand sketches is the difficulty of tuning the parameters involved in the process. Commonly, these parameters are chosen empirically from the observation of segmentation results in training sets. However, this approach rarely gets the best set of parameters, especially when the parameters depend on each other. This work presents an optimization algorithm, based on the simulated annealing technique, which tunes the segmentation parameters to improve segmentation results. The tuning of parameters has been formulated as an optimization problem where the cost function is expressed as the number of errors in the segmentation of a training set. Errors are determined comparing the computer segmentation with the correct one defined during the design of the shapes of the training set. Experimental work used 177 samples of 20 different shapes, achieving a performance ratio of 97.0% for the correct segmentation after tuning of parameters.

References

  1. Azar, S., Couvreury, L., Delfosse, V., Jaspartz, B. and Boulanger, C. (2006). An agent-based multimodal interface for sketch interpretation. In Proceedings of International Workshop on Multimedia Signal Processing (MMSP-06), 488 - 492.
  2. Casella, G., Deufemia, V., Mascardi, V., Costagliola, G. and Martelli, M. (2008). An agent-based framework for sketched symbol interpretation. Journal of Visual Languages and Computing, 19, 225-257.
  3. Davis, R. C., Colwell, B. and Landay, J. A. (2008). KSketch: A 'Kinetic' Sketch Pad for Novice Animators. Proceedings of the twenty-sixth annual SIGCHI conference on Human factors in computing systems. Aesthetics, Awareness, and Sketching, 413-422.
  4. Fernández-Pacheco, D. G., Aleixos, N., Conesa, J. and Contero, M. (2009). Natural interface for sketch recognition. Advances in Intelligent and Soft Computing, 55, 510-519.
  5. Fernández-Pacheco, D. G., Conesa, J., Aleixos, N., Company, P. and Contero, M. (2009). An agent-based paradigm for free-hand sketch recognition. Lecture Notes in Artificial Intelligence, 5883, 345-354.
  6. Flasinski, M., Jurek, J. and Myslinski, S. (2009). Multiagent System for Recognition of Hand Postures. Lecture Notes in Computer Science, 5545, 815-824.
  7. Gelasca, E. D., Salvador, E. and Ebrahimi, T. (2003). Intuitive strategy for parameter setting in video segmentation. Visual communications and image processing, SPIE proceedings series, 5150 (3), 998- 1008.
  8. Iakovidis, D. K., Savelonas, M. A., Karkanis, S. A. and Maroulis, D. E. (2007). A genetically optimized level set approach to segmentation of thyroid ultrasound images. Applied Intelligence, 27 (3), 193-203.
  9. Juchmes, R., Leclercq P. and Azar, S. (2005). A freehandsketch environment for architectural design supported by a multi-agent system. Computers & Graphics, 29 (6), 905-915.
  10. Kirkpatrick, S., Gelatt, C. D. and Vecchi, M. P. (1983). Optimization by Simulated Annealing. Science, 220 (4598), 671-680.
  11. Kouvelis, P. and Chiang, W. C. (1992). A simulated annealing procedure for single row layout problems in flexible manufacturing systems, International Journal of Production Research, 30 (4), 717-732.
  12. Mbogho, A. J. & Scarlatos, L. L. (2007). Genetic parameter tuning for reliable segmentation of colored visual tags. In Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, ACM, 1525-1525.
  13. Mukerjee, A., Agrawal, R. B., Tiwari, N. and Hasan, N. (1997). Qualitative sketch optimization. Artificial intelligence for engineering design, analysis and manufacturing, 11 (4), 311-323.
  14. Taylor, G. W. & Wolf, C. (2004). Reinforcement Learning for Parameter Control of Text Detection in Images and Video Sequences. In Proc. of the IEEE International Conference on Information & Communication Technologies.
  15. Varley, P. & Company, P. (2008). Automated sketching and engineering culture. In Proceedings of VL/HCC Workshop Sketch Tools for Diagramming, 83-92.
  16. Yu, B. (2003). Recognition of freehand sketches using mean shift. In Proceedings of IUI, 204-210.
Download


Paper Citation


in Harvard Style

G. Fernández-Pacheco D., Albert F., Aleixos N., Conesa J. and Contero M. (2011). AUTOMATED TUNING OF PARAMETERS FOR THE SEGMENTATION OF FREEHAND SKETCHES . In Proceedings of the International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2011) ISBN 978-989-8425-45-4, pages 321-329. DOI: 10.5220/0003363903210329


in Bibtex Style

@conference{grapp11,
author={D. G. Fernández-Pacheco and F. Albert and N. Aleixos and J. Conesa and M. Contero},
title={AUTOMATED TUNING OF PARAMETERS FOR THE SEGMENTATION OF FREEHAND SKETCHES},
booktitle={Proceedings of the International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2011)},
year={2011},
pages={321-329},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003363903210329},
isbn={978-989-8425-45-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2011)
TI - AUTOMATED TUNING OF PARAMETERS FOR THE SEGMENTATION OF FREEHAND SKETCHES
SN - 978-989-8425-45-4
AU - G. Fernández-Pacheco D.
AU - Albert F.
AU - Aleixos N.
AU - Conesa J.
AU - Contero M.
PY - 2011
SP - 321
EP - 329
DO - 10.5220/0003363903210329