Images in real world can be categorized based on the mode of capture, information, type i,e nature ,flowers etc. This is of vital importance as the user is interested in retrieving information specific to the category. The images need to be segmented in complex scene for providing the appropriate information. This leads to lot of challenges in real time. This paper presents a complete survey of different image segmentation techniques that are available. The paper offers suggestions for selecting the appropriate technique for segmenting the images based on the different performance parameters. A complete tabulation of the different segmentation techniques analyzed has been presented at the end of the paper. The segmentation techniques has been analyzed considering the edge detection as a vital factor. The paper also provides research directions for using neural approaches for segmentation.

1. Rafael C. Gonzalez and Richard E. woods, "Digital Image Processing", pp. 617-622, 2nd edition, Prentice Hall, 2006.
2. Ranjith Unnikrishnan, Caroline Pantofaru and Martial Hebert, "Toward Objective Evaluation of Image Segmentation Algorithms",IEEE transaction on pattern analysis and machine intelligence ,Vol. 29, No. 6, pp. 929-944, June 2007.
3. Ranjith Unnikrishnan, Caroline Pantofaru and Martial hebert, "Measures of Similarity" Proceedings of the Seventh IEEE Workshop on Applications of Computer Vision, 2005
4. R. Unnikrishnan, C. Pantofaru and M. Hebert, "A Measure for Objective Evaluation of Image Segmentation Algorithms",Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR05), pp. 1063-1069, May 2005.
5. Wei Zhang , Xiang Zhong Fang, Xiaokang Yang, "Moving vehicles segmentation based on Bayesian framework for Gaussian motion model". Pattern Recognition Letters,Volume 27,issue 9,1, pages 956-967, July 2006.
6. Aroh Barjatya, "Block Matching Algorithms For Motion Estimation". In DIP 6620 Spring Final Project Paper, 2004.
7. Gupte, S. , Masoud, O. , Martin, R. F. K. , Papanikolopoulos, N. P. , "Detection and classification of vehicles. "IEEE Trans. Intell. Transport. Syst. , 3, 37-47,2002.
8. Pless,Larson,Siebers,Westover, " Evaluation of local models of dynamic backgrounds". CVPR 2, pp. I/73- I/78, 2003.
9. Franz Pernkopf,Djamel Bouchaffra. "Genetic-Based EM Algorithm for Learning Gaussian Mixture Models". IEEE Transactions On Pattern Analysis And Machine Intelligence, VOL. 27, NO. 8, AUGUST 2005.
10. Toth, D. , Aach, T. , "Detection and recognition of moving objects using statistical motion detection and Fourier descriptors", In ICIAP,,pp. 430-435, 2003.
11. Friedman, N. , Russell, S. , "Image segmentation in video sequences: A probabilistic approach", In: Proc. of 13th Conf. on Uncertainty in Artificial Intelligence,, pp. 175-181, 1997.
12. Ha, D. M. , Lee, J. -M. , Kim, Y. -D. , "Neural-edge-based vehicle detection and traffic parameter extraction", Image Vision Comput. , 22, 899-907, 2004.
13. Lee, K. -W. , Kim, J. ,"'Moving object segmentation based on statistical motion Otsu, N. ," A threshold selection method from Gray-level histograms. " IEEE Trans. Syst. , Man, Cyber. 9 (1), 62-69, 1979.
14. Dempster, A. , Laird, N. , Rubin, D. ," Maximum likelihood from incomplete data via the EM algorithm. "J. Royal Statist. Soc. , Ser. B 39, 1-38, 1977.
15. Elgammal, A. , Duraiswami, R. , Harwood, D. , Davis, L. S. ,"Background and foreground modeling using nonparametric kernel density estimation for visual surveillance",Proc. IEEE 90, 1151 -1163, 2002.
16. Fung, G. S. K. , Yung, N. H. C. , Pang, G. K. H. ,"Camera calibration from road lane markings. "In: Proc. SPIE Optical Engineering,42, pp. 2967-2977, 2003.
17. Li, L. Y. , Huang, W. M. , Gu, I. Y. H. , Tian, Q. ,"Statistical modeling of complex backgrounds for foreground object detection. "IEEE Trans. Image Process. 13, 1459-1472, 2004.
18. Monnet, A. , Mittal, A. , Paragios, N. , Ramesh, V. , " Background modeling and subtraction of dynamic scenes. "In ICCV 2,' pp. 1305- 1312, 2003.
19. Pakorn, K. T. P. , Richard, B. ," A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. "Image Vision Comput. 21, 913-929, 2003.
20. Seki, M. , Wada, T. , Fujiwara, H. , Sumi, K. , " Background Subtraction based on Cooccurrence of Image Variations. "In CVPR 2, pp. II/65-II/72, 2003.
21. Stauffer, C. , Grimson, W. E. L. , " Adaptive background mixture models for real-time tracking. "In CVPR 2, pp. 246-252,1999.
22. Stefano, L. D. , Mattoccia, S. , Mola, M. ," A Change-Detection Algorithm Based on Structure and Color. "In: Proc. of the IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, pp. 252-259, 2003.
23. Sun, Y. , Yuan, B. ," Hierarchical GMM to handle sharp changes in moving object detection. "Electron. Lett. 40, 801-802, 2004.
24. Toyama, K. , Krumm, J. , Brumitt, B. , Meyers, B. ," Wallflower: Principles and practice of background maintenance. "In ICCV, 1, pp. 255-261, 1999model", Electronics Letters. 35, pp. 1719-1720, 1999.
25. T. Zhang, R. Ramakrishnan, and M. Livny, "BIRCH: an efficient data clustering method for very large databases",Proc. ACM SIGMOD Intl Conf. Management of Data (SIGMOD 96), pp. 103-114, 1996.

Edge Feature Vector Neural Network Segmentation Training Function