Integrated region-based segmentation using color components and texture features with prior shape knowledge

Mehryar Emambakhsh; Hossein Ebrahimnezhad; Mohammad Hossein Sedaaghi

International Journal of Applied Mathematics and Computer Science (2010)

  • Volume: 20, Issue: 4, page 711-726
  • ISSN: 1641-876X

Abstract

top
Segmentation is the art of partitioning an image into different regions where each one has some degree of uniformity in its feature space. A number of methods have been proposed and blind segmentation is one of them. It uses intrinsic image features, such as pixel intensity, color components and texture. However, some virtues, like poor contrast, noise and occlusion, can weaken the procedure. To overcome them, prior knowledge of the object of interest has to be incorporated in a top-down procedure for segmentation. Consequently, in this work, a novel integrated algorithm is proposed combining bottom-up (blind) and top-down (including shape prior) techniques. First, a color space transformation is performed. Then, an energy function (based on nonlinear diffusion of color components and directional derivatives) is defined. Next, signeddistance functions are generated from different shapes of the object of interest. Finally, a variational framework (based on the level set) is employed to minimize the energy function. The experimental results demonstrate a good performance of the proposed method compared with others and show its robustness in the presence of noise and occlusion. The proposed algorithm is applicable in outdoor and medical image segmentation and also in optical character recognition (OCR).

How to cite

top

Mehryar Emambakhsh, Hossein Ebrahimnezhad, and Mohammad Hossein Sedaaghi. "Integrated region-based segmentation using color components and texture features with prior shape knowledge." International Journal of Applied Mathematics and Computer Science 20.4 (2010): 711-726. <http://eudml.org/doc/208020>.

@article{MehryarEmambakhsh2010,
abstract = {Segmentation is the art of partitioning an image into different regions where each one has some degree of uniformity in its feature space. A number of methods have been proposed and blind segmentation is one of them. It uses intrinsic image features, such as pixel intensity, color components and texture. However, some virtues, like poor contrast, noise and occlusion, can weaken the procedure. To overcome them, prior knowledge of the object of interest has to be incorporated in a top-down procedure for segmentation. Consequently, in this work, a novel integrated algorithm is proposed combining bottom-up (blind) and top-down (including shape prior) techniques. First, a color space transformation is performed. Then, an energy function (based on nonlinear diffusion of color components and directional derivatives) is defined. Next, signeddistance functions are generated from different shapes of the object of interest. Finally, a variational framework (based on the level set) is employed to minimize the energy function. The experimental results demonstrate a good performance of the proposed method compared with others and show its robustness in the presence of noise and occlusion. The proposed algorithm is applicable in outdoor and medical image segmentation and also in optical character recognition (OCR).},
author = {Mehryar Emambakhsh, Hossein Ebrahimnezhad, Mohammad Hossein Sedaaghi},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {image segmentation; prior shape knowledge; level set; nonlinear diffusion; energy minimization},
language = {eng},
number = {4},
pages = {711-726},
title = {Integrated region-based segmentation using color components and texture features with prior shape knowledge},
url = {http://eudml.org/doc/208020},
volume = {20},
year = {2010},
}

TY - JOUR
AU - Mehryar Emambakhsh
AU - Hossein Ebrahimnezhad
AU - Mohammad Hossein Sedaaghi
TI - Integrated region-based segmentation using color components and texture features with prior shape knowledge
JO - International Journal of Applied Mathematics and Computer Science
PY - 2010
VL - 20
IS - 4
SP - 711
EP - 726
AB - Segmentation is the art of partitioning an image into different regions where each one has some degree of uniformity in its feature space. A number of methods have been proposed and blind segmentation is one of them. It uses intrinsic image features, such as pixel intensity, color components and texture. However, some virtues, like poor contrast, noise and occlusion, can weaken the procedure. To overcome them, prior knowledge of the object of interest has to be incorporated in a top-down procedure for segmentation. Consequently, in this work, a novel integrated algorithm is proposed combining bottom-up (blind) and top-down (including shape prior) techniques. First, a color space transformation is performed. Then, an energy function (based on nonlinear diffusion of color components and directional derivatives) is defined. Next, signeddistance functions are generated from different shapes of the object of interest. Finally, a variational framework (based on the level set) is employed to minimize the energy function. The experimental results demonstrate a good performance of the proposed method compared with others and show its robustness in the presence of noise and occlusion. The proposed algorithm is applicable in outdoor and medical image segmentation and also in optical character recognition (OCR).
LA - eng
KW - image segmentation; prior shape knowledge; level set; nonlinear diffusion; energy minimization
UR - http://eudml.org/doc/208020
ER -

References

top
  1. Andreopoulos, A. and Tsotsos, J.K. (2010). Cardiac MRI dataset, www.cse.yorku.ca/mridataset/. 
  2. Andrysiak, T. and Choras, M. (2005). Image retrieval based on hierarchical Gabor filters, International Journal of Applied Mathematics and Computer Science 15(4): 471-480. Zbl1134.94308
  3. Biasdy, F., El-Sana, J. and Habash, N. (2006). Online arabic handwriting recognition using hidden Markov models, Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition, La Baule, France. 
  4. Cheng, H., Jing, X.H., Sun, Y. and Wang, J. (2001). Color image segmentation: Advances and prospects, Pattern Recognition 34(12): 2259-2281. Zbl0991.68137
  5. Cremers, S.D., Rousson, M. and Deriche, R. (2007). A review of statistical approaches to level sets segmentation: Integrating colour, texture, motion and shape, International Journal of Computer Vision 72(2): 195-215. 
  6. Dokur, Z., Iscan, Z. and Olmez, T. (2006). Segmentation of medical images by using wavelet transform and incremental self-organizing map, in A. Gelbukh and C.A. Reyes-Garcia (Eds.) MICAI 2006: Advances ina Artificial Intelligence, Lecture Notes in Computer Science, Vol. 4293, Springer, Berlin/Heidelberg, pp. 800-809. 
  7. Einsele, F., Ingold, R. and Hennebert, J. (2008). A languageindependent, open-vocabulary system based on hmms for recognition of ultra low resolution words, Journal of Universal Computer Science 14(18): 2982-2997. 
  8. Emambakhsh, M., Ebrahimnezhad, H. and Sedaaghi, M.H. (2010). A hybrid top-down/bottom up approach for image segmentation incorporating color and texture with prior shape knowledge, 18th Iranian Conference on Electrical Engineering ICEE2010, Isfahan, Iran, pp. 270-275. Zbl1209.94006
  9. Emambakhsh, M. and Sedaaghi, M.H. (2009). Automatic MRI brain segmentation using local features, self-organizing maps, and watershed, IEEE International Conference on Signal and Image Processing Applications, Kuala Lumpur, Malaysia, pp. 123-128. 
  10. Feddern, C., Weickert, J. and Burgeth, B. (2006). Levelset methods for tensor-valued images, Proceedings of the IEEE 2nd Workshop on VLSM, Nice, France, pp. 65-72. 
  11. Forsyth, D.A. and Ponce, J. (2002). Computer Vision: A Modern Approach, Prentice-Hall of India, New Dehli. 
  12. Gerig, G., Kbler, O., Kikinis, R. and Jolesz, F.A. (1992). Nonlinear anisotropic filtering of MRI data, IEEE Transactions on Medical Imaging 11(2): 221-232. 
  13. Goldberg, D.E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA. Zbl0721.68056
  14. Greig, D., Porteous, B. and Seheult, A. (1989). Exact maximum a posteriori estimation for binary images, Journal of the Royal Statistical Society. Series B (Methodological) 51(2): 271-279. 
  15. Hao, J., Shen, Y. and Wang, Q. (2007). Segmentation for MRA image: An improved level-set approach, IEEE Transactions on Instrumentation and Measurement 56(4): 1316-1321. 
  16. Hrebien, M., Stec, P., Nieczkowski, T. and Obuchowicz, A. (2008). Segmentation of breast cancer fine needle biopsy cytological images, International Journal of Applied Mathematics and Computer Science 18(2): 159-170, DOI: 10.2478/v10006-008-0015-x. Zbl1228.92045
  17. Jain, A.K. (1989). Fundamentals of Digital Image Processing, Prentice Hall, Englewood Cliffs, NJ. Zbl0744.68134
  18. Kass, M., Witkin, A. and Terzopoulos, D. (1988). Snakes, active contour model, International Journal of Computer Vision 1(4): 321-331. 
  19. Kirkpatrick, S., Gelatt, C.D. and Vecchi, M.P. (1983). Optimization by simulated annealing, Science Magazine 220(4598): 671-680. Zbl1225.90162
  20. Kuo, W., Lin, C. and Sun, Y. (2008). Brain MR images segmentation using statistical ratio: Mapping between watershed and competitive Hopfield clustering network algorithms, Computer Methods and Programs in Biomedicine 91(3): 191-198. 
  21. Lai, C. and Chang, C. (2009). A hierarchical evolutionary algorithm for automatic medical image segmentation, Expert Systems with Applications 36(1): 248-259. 
  22. Levenberg, K. (1944). A method for the solution of certain problems in least-squares, Quarterly Applied Mathematics 2(2): 164-168. Zbl0063.03501
  23. Lewis, Michael, R. and Torczon, V. (1999). Pattern search algorithms for bound constrained minimization, SIAM Journal on Optimization 9(4): 1082-1099. Zbl1031.90047
  24. Lu, Y., Wang, J., Kong, J., Zhang, B. and Zhang, J. (2006). An integrated algorithm for MRI brain images segmentation, Computer Vision Approaches to Medical Image Analysis 4241: 132-142. 
  25. Mitiche, A. and Sekkati, H. (2006). Optical flow 3d segmentation and interpretation: A variational method with active curve evolution and level sets, IEEE Transactions on Pattern Analysis and Machine Intelligence 28(11): 1818-1829. 
  26. Ong, S.H., Yeo, N.C., Lee, K.H., Venkatesh, Y.V. and Kao, D.H. (2002). Segmentation of color images using a twostage self-organizing network, Image and Vision Computing 20(4): 279-289. 
  27. Osher, S. and Sethian, J. (1988). Fronts propagating with curvature dependent speed: Algorithms based on HamiltonJacobi formulations, Journal of Computationl Physics 79(1): 12-49. Zbl0659.65132
  28. Perona, P. and Malik, J. (1990). Scale space and edge detection using anisotropic diffusion, IEEE Transactions on Pattern Analysis and Machine Intelligence 12(7): 629-639. 
  29. Petera, Z., Boussone, V., Bergote, C. and Peyrina, F. (2008). Aconstrained region growing approach based on watershed for the segmentation of low contrast structures in bone micro-CT images, Pattern Recognition 41(7): 2358-2368. 
  30. Raja, K. B., Madheswaran, M. and Thyagarajah, K. (2010). Texture pattern analysis of kidney tissues for disorder identification and classification using dominant Gabor wavelet, Machine Vision and Applications 21(3): 287-300. 
  31. Ramme, A.J., DeVries, N., Kallemyn, N.A., Magnotta, V.A. and Grosland, N. M. (2009). Semi-automated phalanx bone segmentation using the expectation maximization algorithm, Journal of Digital Imaging 22(5): 483-491. 
  32. Ranganathan, A. (2004). The Levenberg-Marquardt algorithm, Technical report http://www.scribd.com/doc/10093320/Levenberg-Marquardt-Algorithm. 
  33. Rousson, M., Brox, T. and Deriche, R. (2003). Active unsupervised texture segmentation on a diffusion based feature space, Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA, pp. 699-704. 
  34. Roweis, S. (n.d.). Levenberg-Marquardt optimization, http://www.cs.nyu.edu/roweis/notes/lm.pdf. 
  35. Sandler, R. and Lindenbaum, M. (2006). Gabor filter analysis for texture segmentation, Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06), New York, NY, USA, p. 178. 
  36. Skarbek, W. and Koschan, A. (1994). Color image segmentation-A survey, Technical report, University of Berlin, Berlin. 
  37. Sagiv, C., Sochen, N.A., and Zeevi, Y.Y. (2006). Integrated active contours for texture segmentation, IEEE Transactions on Image Processing 16(6): 1633-1646. 
  38. Susomboon, R., Raicu, D. and Furst, J. (2006). Automatic single-organ segmentation in computed tomography images, Sixth IEEE International Conference on Data Mining (ICDM'06), Hong Kong, China, pp. 1081-1086. 
  39. The-ViewCVS-Group (2010). Caltech 101 dataset, http://grey.colorado.edu. 
  40. Torczon, V. (1997). On the convergence of pattern search algorithms, SIAM Journal on Optimization 7(1): 1-25. Zbl0884.65053
  41. Tsai, A., Yezzi, A., Wells, J.W., Tempany, C., Tucker, D., Fan, A., Grimson, W.E. and Willsky, A. (2003). A shapebased approach to the segmentation of medical imagery using level sets, IEEE Transactions on Medical Imaging 22(2): 137-154. 
  42. Vincent, L. and Soille, P. (1991). Watersheds in digital spaces: An efficient algorithm based on immersion simulations, Pattern Analysis and Machine Intelligence 13(6): 583-598. 
  43. Wang, J., Kong, J., Lu, Y., Qi, M. and Zhang, B. (2008). A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints, Computerized Medical Imaging and Graphics 32(8): 685-698. 
  44. Wang, Z. and Vemuri, B.C. (2004). An affine invariant tensor dissimilarity measure and its applications to tensor-valued image segmentation, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, pp. 228-233. 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.