Advertisement

Object Tracking In Image Sequence Combining Hausdorff Distance, Non-Extensive Entropy In Level Set Formulation

  • Paulo S. S. Rodrigues
  • Gilson A. Giraldi
  • Ruey-Feng Chang
  • Jasjit S. Suri
Part of the Topics in Biomedical Engineering. International Book Series book series (ITBE)

The task of Object Recognition is one of the most important problems in computational vision systems. Generally, to meet this problem, specific approaches are applied in two phases: detecting the region of interest and tracking them around a frame sequence. For applications such as medical images or general object tracking, current methodologies generally are machine dependent or have high speckle noise sensitivity. In a sequence of ultrasound images some data are often missing if the approach does not use lesiontracking methods. Also, the segmentation process is highly sensitive to noise and changes in illumination. In this chapter we propose a four-step method to handle the first phase of the problem. The idea is to track the region of interest using the information found in the previous slice to search for the ROI in the current one. In each image (frame) we accomplish segmentation with Tsallis entropy, which is a new kind of entropy for nonextensive systems. Then, employing the Hausdorff distance we match candidate regions against the ROI in the previous image. In the final step, we use the ROI curve to compute a narrow band that is an input for an embedded function in a level set formulation, smoothing the final shape. We have tested our method with three classes of images: a general indoor office, a Columbia database, and low-SNR ultrasound images of breast lesions, including benign and malignant tumors, and have compared our proposed method with the Optical Flow Approach.

Keywords

Breast Lesion Object Tracking Hausdorff Distance Mammographic Image Tsallis Entropy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chen CM, Chou YH, Han KC, Hung GS, Tiu CM, Chiou HJ, Chiou SY. 2003. Breast lesion on sonograms: computer-aided diagnosis with neural setting-independent features and artificial neural networks. J Radiol 226:504-514.CrossRefGoogle Scholar
  2. 2.
    Zheng Y, Greenleaf JF, Gisvold JJ. 1997. Reduction of breast biopsies with a modified self-organizing map. IEEE Trans Neural Networks 8:1386-1396.CrossRefGoogle Scholar
  3. 3.
    Brown ML, Houn F, Sickles EA, Kessler LG. 1995. Screening mammography in community prac-tice: positive predictive value of abnormal findings and yield of follow-up diagnostic procedures. AJR Am J Roentgenol 165:1373-1377.Google Scholar
  4. 4.
    Tsallis C. 1999. Nonextensive statistics: theoretical, experimental and computational evidences and connections. Braz J Phys 29(1):1-35.CrossRefGoogle Scholar
  5. 5.
    Tsallis C. 2001. Nonextensive statistical mechanics and its applications. In Lecture notes in physics, Vol. 560, pp. 1128-154. Springer, Berlin. Bibliography of subjects is regularly updated at http://tsallis.cat.cbpf.br/biblio.htm.
  6. 6.
    Albuquerque MP, Albuquerque MP, Esquef IA, Mello ARG. 2004. Image thresholding using Tsallis entropy. Pattern Recognit Lett 25:1059-1065.CrossRefGoogle Scholar
  7. 7.
    Xu H, Younis A, Kabuka MR. 2004. Automatic moving object extraction for content-based ap-plications. IEEE Trans Circ Syst Video Technol 14(6):796-812.CrossRefGoogle Scholar
  8. 8.
    Paragios N, Deriche R. 2000. Geodesic active contours and level sets for detection and tracking of moving objects. IEEE Trans Pattern Anal Machine Intell 22:266-280.CrossRefGoogle Scholar
  9. 9.
    Kim C, Hwang J. 2002. Fast and automatic video object segmentation and tracking for content-based applications. IEEE Trans Circ Syst Video Technol 12(3):122-129.Google Scholar
  10. 10.
    Luo Y, Wu T, Hwang J. 2003. Object-based analysis and interpretation of human motion in sports video sequences by dynamic bayesian networks. Comput Vision Image Understand 92(2-3):196-216.CrossRefGoogle Scholar
  11. 11.
    Gao J, Hauptmann AG, Wactlar HD. 2004. Combining motion segmentation with tracking for activity analysis. In Proceedings of the IEEE international conference on automatic face and gesture recognition (FGR’04), pp. 699-704. Washington, DC: IEEE Computer Society.Google Scholar
  12. 12.
    Sheidermann H, Kanade T. 2000. A statistical method for 3d object detection applied to faces and cars. In Proceedings of the IEEE Conference on computer vision and pattern recognition, Vol. 1, pp. 746-751. Washington, DC: IEEE Computer Society.Google Scholar
  13. 13.
    Lim J, Kriegman D. 2004. Tracking humans using prior and learned representation of shape and appearance. In Proceedings of the IEEE international conference on automatic face and gesture recognition (FGR’04), pp. 869-874. Washington, DC: IEEE Computer Society.Google Scholar
  14. 14.
    Yeasin M, Polat E, Sharma R. 2004. A multiobject tracking framework for interactive multimedia applications. IEEE Transaction on Multimedia 6(3):398-405.CrossRefGoogle Scholar
  15. 15.
    Cox IJ, Hingorani SL. 1996. An efficient implementation of Reid’s multiple hypotesis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans Pattern Anal Machine Intell 18:138-150.CrossRefGoogle Scholar
  16. 16.
    Rodrigues PS, Albuquerque A. 2002.A region-based object recognition algorithm. In Proceedings of the 15th Brazilian symposium on computer graphics and image processing (SIBGRAPI 2002), pp. 283-290. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  17. 17.
    Rodrigues PS, Rodrigues DMC, Giraldi GA, Silva RLS. 2004. A Bayesian network model for ob-ject recognition environment using color features. In Proceedings of the 17th Brazilian symposium on computer graphics and image processing (SIBGRAPI 2004). Electronic Proceedings.Google Scholar
  18. 18.
    Rodrigues PS, Rodrigues DMC, Giraldi GA, Silva RLS. 2004. Object recognition using Bayesian networks for augmented reality applications. In Proceedings of the 7th symposium on virtual reality (SVR’04). Available at http://virtual.lncc.br/ diego/Artigos/Accepteds/SVR-2004.pdf.
  19. 19.
    Chen DR, Chang RF, Huang YL. 1999. Computer-aided diagnosis applied to solid breast nodules by using neural networks. J Radiol 213:407-412.Google Scholar
  20. 20.
    Garra BS, Krasner BH, Horii SC, Ascher S, Mun SK. 1993. Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis. Ultrason Images 15:267-285.CrossRefGoogle Scholar
  21. 21.
    Sakira A, Shikamoto K, Satake H, Ishigaki T, Koyama S, Obata Y, Ikeda M. 1999. Breast ul-trasonography: diagnostic efficacy of computer-aided diagnostic system using fuzzy inference. Radiat Med 17:41-45.Google Scholar
  22. 22.
    Chang RF, Kuo WJ, Chen DR, Huang YL, Lee JH, Chou YH. 2000. Computer-aided diagnosis for surgical office-based breast ultrasound. Arch Surg 135(6):696-699.CrossRefGoogle Scholar
  23. 23.
    Chang RF, Wu WJ, Moon WK, Chen DR. 2003. Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis. Ultrasound Med Biol 29(5):679-668.CrossRefGoogle Scholar
  24. 24.
    Drukker K, Giger ML, Horsch K, Kupinski MA, Vyborny CJ, Mendelson EB. 2002. Computerized lesion detection on breast ultrasound. Med Phys 29(7):1438-1446.CrossRefGoogle Scholar
  25. 25.
    Horsch K, Giger ML, Venta LA, Vyborny CJ. 2002. Computerized diagnosis of breast lesions on ultrasound. Med Phys 29(2):157-164.CrossRefGoogle Scholar
  26. 26.
    Chen DR, Kuo WJ, Chang RF, Moon WK, Lee CC. 2002. Use of the bootstrap technique with small training sets for computer-aided diagnosis in breast ultrasound. Ultrasound Med Biol 28(7):897-902.CrossRefGoogle Scholar
  27. 27.
    Chen DR, Chang RF, Huang YL. 1999. Computer-aided diagnosis applied to solid breast nodules by using neural networks. Radiology 213(2):407-412.Google Scholar
  28. 28.
    Kuo WJ, Chang RF, Moon WK, Lee CC, Chen DR. 2002. Computer-aided diagnosis of breast tumors with different us systems. Acad Radiol 9(7):793-799.CrossRefGoogle Scholar
  29. 29.
    Huttenlocher DP, Noh JJ, Rucklidge WJ. 1992. Tracking non-rigid objects in complex scenes. Technical Report 1320, Department of Computer Science, Cornell University.Google Scholar
  30. 30.
    Huttenlocher DP, Klanderman GA, Rucklidge WJ. 1993. Comparing images using the Hausdorff distance. IEEE Trans Med Imaging 15(9):850-863.Google Scholar
  31. 31.
    Chalana V, Kim Y. 1997. A methodology for evaluation of boundary detection algorithms on medical images. IEEE Trans Med Imaging 16(5):642-652.CrossRefGoogle Scholar
  32. 32.
    Bamford P. 2003. Automating cell segmentation evaluation with annotated examples. In Proceed-ings of the APRS workshop on digital image computing, (WDCI 2003), pp. 21-25. Available at http://www.aprs.org.au/wdic2003/CDROM/21.pdf.
  33. 33.
    Shannon C, Weaver W. 1948. The mathematical theory of communication. Urbana: U Illinois P.Google Scholar
  34. 34.
    Yamano T. 2001. Information theory based in nonadditive information content. Entropy 3:280-292.MATHCrossRefGoogle Scholar
  35. 35.
    Kapur JN, Sahoo PK, Wong AKC. 1985. A new method for gray-level picture thresholding using the entropy of the histogram. Comput Graphics Image Process 29:273-285.CrossRefGoogle Scholar
  36. 36.
    Abutaleb AS. 1989. A new method for gray-level picture thresholding using the entropy of the histogram. Comput Graphics Image Process 47:22-32.CrossRefGoogle Scholar
  37. 37.
    Li CH, Lee CK. 1993. Minimum cross-entropy thresholding. Pattern Recognit 26:617-625.CrossRefGoogle Scholar
  38. 38.
    Sahoo PK, Soltani S, Wong AKC. 1988. A survey of thresholding techiniques. Comput Vis Graph- ics Image Process 41:233-260.CrossRefGoogle Scholar
  39. 39.
    Pun T. 1981. Entropic thresholding: a new approach. Comput Graphics Image Process 16:210-239.CrossRefGoogle Scholar
  40. 40.
    Osher SJ, Sethian JA. 1988. Fronts propagation with curvature dependent speed: Algorithm based on Hamilton-Jacobi formulations. J Comput Phys 79:12-49.MATHCrossRefMathSciNetGoogle Scholar
  41. 41.
    Sethian JA. 1999. Level set methods and fast marching methods: evolving interfaces in compu-tational geometry, fluid mechanics, computer vision, and materials science, 2nd ed. New York: Cambridge UP.Google Scholar
  42. 42.
    Malladi R, Sethian JA, Vemuri BC. 1995. Shape modeling with front propagation: a level set approach. IEEE Trans Pattern Anal Machine Intell 17(2):158-175.CrossRefGoogle Scholar
  43. 43.
    McInerney TJ. 1997. Topologically adaptable deformable models for medical image analysis. PhD dissertation, Department of Computer Science, University of Toronto.Google Scholar
  44. 44.
    ter Haar Romery BM, Niessen WJ, Viergever MA. 1998. Geodesic deformable models for medical image analysis. IEEE Trans Med Imaging 17(4):634-641.CrossRefGoogle Scholar
  45. 45.
    Sethian JA. 1996. Level set methods: evolving interfaces in geometry, fluid mechanics, computer vision and materials sciences. New York: Cambridge UP.Google Scholar
  46. 46.
    Suri JS, Liu K, Singh S, Laxminarayan S, Zeng X, Reden L. 2002. Shape recovery algorithms using level sets in 2-d/3-d medical imagery: a state-of-the-art review. IEEE Trans Inf Technol Biomed 6(1):8-28.CrossRefGoogle Scholar
  47. 47.
    Mauch S. 2000. A fast algorithm for computing the closest point and distance function. Technical Report, CalTech.Google Scholar
  48. 48.
    Sigg C, Peikert R. 2005. Optimized bounding polyhedra for gpu-based distance transform. Pro-ceedings of Dagstuhl seminar 023231 on scientific visualization: extracting information and knowledge from scientific data sets. Berlin: Springer. Available at http://graphics.ethz.ch/ peik-ert/papers/dagstuhl03.pdf/.
  49. 49.
    Giraldi GA, Rodrigues PS, Marturelli LS, Silva RLS. 2005. Improving the initialization, conver-gence and memory utilization for deformable models. In Segmentation models, Vol. 1. Part A of Handbook of Image Analysis, Part A, 2nd ed., pp. 359-414. Berlin: Springer.Google Scholar
  50. 50.
    Columbia object image library (COIL-100). Department of Computer Science, Columbia Uni-versity. http://www.cs.columbia.edu/CAVE/research/softlib/coil-100.html.
  51. 51.
    Lucas B, Kanade T. 1981. An iterative image registration technique with an application to stereo vision. In Proceedings of the DARPA Image Understanding Workshop, pp. 121-130. Washington, DC: US Government Printing Office.Google Scholar
  52. 52.
    Suri J. 1998. Error and shape measurement tools for cardiac projection images: a closer look. Proceedings of an international conference in applications of patterns recognition, pp. 125-134.Google Scholar
  53. 53.
    Suri J, Haralick RM, Sheehan FH. 1996. Greedy algorithm for error reduction in automatically produced boundaries from low contrast ventriculogram. Proceedings of the international confer-ence on pattern recognition (ICPR’96), Vol. 4, pp. 361-365. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  54. 54.
    Suri J, Haralick RM, Sheehan FH. 2000. Greedy algorithm for error reduction in automatically produced boundaries from low contrast ventriculogram. Int J Pattern Anal Appl 3(1):39-60.CrossRefGoogle Scholar
  55. 55.
    Suri J, Setarhedran SK, Singh S. 2002. Advanced algorithm approaches to medical image seg-menttion: state-of-the-art applications in cardiology, neurology, mammography and pathology. Berlin: Springer.Google Scholar
  56. 56.
    Giraldi GA, OliveiraAAF. 1999. Dual-snake model in the framework of simplicial domain decom-position. Technical poster at the international symposium on computer graphics, image processing and vision (SIBGRAPI’99), pp. 103-106. Washington, DC: IEEE Computer Society.Google Scholar
  57. 57.
    Giraldi GA, Gonvalvez LMG, Oliveira AAF. 2000. Dual topologically adaptable snakes. In Pro-ceedings of the fifth joint conference on information sciences (JCIS 2000), third international conference on computer vision, pattern recognition, and image processing, Vol. 2, pp. 103-106. Washington, DC: IEEE Computer Society.Google Scholar
  58. 58.
    Giraldi GA, Strauss E, Oliveira AAF. 2000. A boundary extraction method based on dual-t-snakes and dynamic programming. In Proceedigns of the IEEE computer society conference on computer vision and pattern recognition, (CVPR 2000), p. 1044. Washington, DC: IEEE Computer Society.Google Scholar
  59. 59.
    Giraldi GA, Gonzalves LMG, Oliveira AAF. 2000. Automating cell segmentation evaluation with annotaded examples. In Proceedings of the APRS workshop on digital image computing, (WDCI 2000), Vol. 2, pp. 103-107. Washington, DC: IEEE Computer Society.Google Scholar
  60. 60.
    Giraldi GA, Schaefer L, Rodrigues PS. 2005. Gradient vector flow models for boundary extraction in 2d images. In Proceedings of the 8th international conference on computer graphics and image (IASTED CGIM 2005’, p. 2000. Washington, DC: IEEE Computer Society.Google Scholar
  61. 61.
    Giraldi GA, Strauss E, Oliveira AAF. 2000. Boundary extraction approach based on multi-resolution methods and the t-snakes framework. In Proceedings of the 13th Brazilian symposium on computer graphics and image processing (SIBGRAPI 2000), pp. 82-89. Washington, DC: IEEE Computer Society.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Paulo S. S. Rodrigues
    • 1
  • Gilson A. Giraldi
    • 1
  • Ruey-Feng Chang
    • 2
  • Jasjit S. Suri
    • 3
  1. 1.National Laboratory for Scientific ComputingQuitandinhaBrazil
  2. 2.Department of Computer Science and Information EngineeringNational Chung Cheng UniversityTaiwan
  3. 3.Biomedical Research InstituteIdaho State UniversityPocatelloUSA

Personalised recommendations