Abstract
Segmentation is one of the most important steps leading to the analysis of processed image data. This paper describes a segmentation system based on the application of Total Gradient Histogram Method (TGH) and Relative Contrast Method (RC). The implementation is processed in two strategies. In the first strategy, we implement monothresholding. The second strategy based on multithresholding is processed through three steps: highest thresholds, highest thresholds by range of grey level, and hierarchical thresholding segmentation. Through all implementations approaches on stereoscopic scenes, an other process using a rule based system is done in order to improve segmentation results. Finally, we apply our algorithms of segmentation to images from many other domains.
This is a preview of subscription content, log in via an institution to check access.
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
Canny, J.F.: A computational approach to edge detection. PAMIÂ 8(6) (November 1986)
Chen, S.Y., Lin, W.C., Chen, C.T.: Split-and-merge image segmentation based on localised feature analysis and statistical tests. CVGIP Graphical Models and Image Processing (1991)
Cord, M., Huet, F., Philipp, S.: Optimal adjusting of edge detectors to extract close contours. In: Proc. 10th Scandinavian Conference on Image Analysis, Lappeenranta, Finlande (June 1997)
Demigny, D., Kamleh, T.: A Discrete expression of Canny’s Criteria for Step Edge Detection Performances Evaluation. IEEE Pattern Analysis and Machine Intelligence (1997)
Deriche, R.: Optimal Edge Detection Using Recursive filtering. In: First International Conference on Computer Vision, London (1987)
Huet, F., Philipp, S.: High-scale edge study for segmentation and contour closing in textured or noisy images. In: IEEE SSIAI 1998, Tucson, Arizona, USA (Avril 1998)
Kohler, R.: A segmentation system based on thresholding. Computer Graphics and Image Processing 4(3)
Martelli, A.A.: « Edge detection using heuristic search methods ». In: CGIP, August 1972, vol. 1 (1972)
Nilsson, N.J.: Principals of Artificial Intelligence. Springer, Berlin (1982)
Pavlidis, T., Horowitz, H.: « Picture Segmentation by a Directed Split-and-merge Procedure ». In: Proc 2nd IJCPR, Août (1974)
Randriamasy, S.: Segmentation descendante cooperative en régions de pairesd’images stéréoscopiques, PhD thesis, University Paris IX-Dauphine
Reddy, D.R., Ohlander, R., Price, K.: Picture segmentation using a recursive region splitting method. Computer graphics and Image processing 8 (1978)
Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis and Machine Vision. Chapmen & Hall Computing, London (1993)
Zagrouba, E., Krey, C.: A rule-based system for region segmentation improvement in sterevision. In: IS&T-SPIE International Technical Conference of San Jose. Image and Video Processing II, California-USA, Février 7-9, vol. 21-82, pp. 357–367 (1994)
Zagrouba, E.: Construction de Facettes Tridimensionnelles par Mise en Correspondance de Régions en Stéréovision, PhD Thesis INP Toulouse, France, Septembre (1994)
Zagrouba, E.: 3-D facets constructor for stereovision. In: 5th International Conference on Artificial Intelligence, Rome, Italie (September 1997)
Zucker, W.: Region growing Childhood and adolescence. Computer Graphics and Image Processing, 382 (1976)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zagrouba, E., Hedidar, T., Jaoua, A. (1999). A Robust and Unified Algorithm for Indoor and Outdoor Scenes Based on Region Segmentation. In: Imam, I., Kodratoff, Y., El-Dessouki, A., Ali, M. (eds) Multiple Approaches to Intelligent Systems. IEA/AIE 1999. Lecture Notes in Computer Science(), vol 1611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48765-4_61
Download citation
DOI: https://doi.org/10.1007/978-3-540-48765-4_61
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66076-7
Online ISBN: 978-3-540-48765-4
eBook Packages: Springer Book Archive