Call for Paper - October 2019 Edition
IJCA solicits original research papers for the October 2019 Edition. Last date of manuscript submission is September 20, 2019. Read More

Probabilistic Relaxation Labeling: A Short Survey on Object Recognition

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2019
Abbas Zohrevand

Abbas Zohrevand. Probabilistic Relaxation Labeling: A Short Survey on Object Recognition. International Journal of Computer Applications 181(38):40-44, January 2019. BibTeX

	author = {Abbas Zohrevand},
	title = {Probabilistic Relaxation Labeling: A Short Survey on Object Recognition},
	journal = {International Journal of Computer Applications},
	issue_date = {January 2019},
	volume = {181},
	number = {38},
	month = {Jan},
	year = {2019},
	issn = {0975-8887},
	pages = {40-44},
	numpages = {5},
	url = {},
	doi = {10.5120/ijca2019918387},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Object recognition problem can be defined as classifying input object(s) to number of predefined classes. Object recognition is one of the most important sections in computer vision. While this filed has been studied from long time ago, but it still suffers from several challenges such as: occlusion, rotation, distortion illumination, and scaling. The conventional object recognition system has two phases. Firstly: extraction of the most important (informatics or key pints) parts from object image (scene image) and predefined class image (model image), secondly matching between object and model. The Probabilistic Relaxation Labeling (PRL) is one of the popular probabilistic approaches in matching among model and scene. In this paper we review two phase and report the most important works based PRL.


  1. A. R. Ahmadyfard and J. Kittler, “Using relaxation technique for region-based object recognition,” Image Vis. Comput., vol. 20, no. 11, pp. 769–781, 2002.
  2. R. T. Chin and C. R. Dyer, “Model-based recognition in robot vision,” ACM Comput. Surv., vol. 18, no. 1, pp. 67–108, 1986.
  3. H. Murase and S. K. Nayar, “Visual learning and recognition of 3-D objects from appearance,” Int. J. Comput. Vis., vol. 14, no. 1, pp. 5–24, 1995.
  4. H. J. Wolfson, “Model-based object recognition by geometric hashing,” in Computer Vision—ECCV 90, Springer, 1990, pp. 526–536.
  5. S. Procter and J. Illingworth, “Foresight: Fast object recognition using geometric hashing with edge-triple features,” in Image Processing, 1997. Proceedings., International Conference on, 1997, vol. 1, pp. 889–892.
  6. A. Leonardis and H. Bischof, “Robust recognition using eigenimages,” Comput. Vis. Image Underst., vol. 78, no. 1, pp. 99–118, 2000.
  7. C.-Y. Huang, O. I. Camps, and T. Kanungo, “Object recognition using appearance-based parts and relations,” in Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, 1997, pp. 877–883.
  8. R. C. Nelson and A. Selinger, “A cubist approach to object recognition,” in Computer Vision, 1998. Sixth International Conference on, 1998, pp. 614–621.
  9. [C. Schmid and R. Mohr, “Local grayvalue invariants for image retrieval,” Pattern Anal. Mach. Intell. IEEE Trans., vol. 19, no. 5, pp. 530–535, 1997.
  10. D. G. Lowe, “Object recognition from local scale-invariant features,” Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, vol. 2. pp. 1150–1157 vol.2, 1999.
  11. A. Shokoufandeh, I. Marsic, and S. J. Dickinson, “View-based object recognition using saliency maps,” Image Vis. Comput., vol. 17, no. 5, pp. 445–460, 1999.
  12. J.-M. Morel and G. Yu, “ASIFT: A new framework for fully affine invariant image comparison,” SIAM J. Imaging Sci., vol. 2, no. 2, pp. 438–469, 2009.
  13. C. Ancuti and P. Bekaert, “SIFT-CCH: Increasing the SIFT distinctness by Color Co-occurrence Histograms,” in Image and Signal Processing and Analysis, 2007. ISPA 2007. 5th International Symposium on, 2007, pp. 130–135.
  14. H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “Speeded-up robust features (SURF),” Comput. Vis. image Underst., vol. 110, no. 3, pp. 346–359, 2008.
  15. W. E. L. Grimson and D. P. Huttenlocher, “On the sensitivity of the Hough transform for object recognition,” Pattern Anal. Mach. Intell. IEEE Trans., vol. 12, no. 3, pp. 255–274, 1990.
  16. D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vis., vol. 60, no. 2, pp. 91–110, 2004.
  17. A. Rosenfeld and S. W. Zucker, “Scene Labeling,” no. 6, pp. 420–433, 1976.
  18. A. Ahmadyfard and J. Kittler, “Region-based representation for object recognition by relaxation labelling,” in Advances in Pattern Recognition, Springer, 2000, pp. 297–307.
  19. K. Mikolajczyk and C. Schmid, “Indexing based on scale invariant interest points,” in Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, 2001, vol. 1, pp. 525–531.
  20. D. L. Waltz, “Generating semantic description from drawings of scenes with shadows,” 1972.
  21. A. Rosenfeld, R. A. Hummel, and S. W. Zucker, “Scene Labeling by Relaxation Operations,” Systems, Man and Cybernetics, IEEE Transactions on, vol. SMC-6, no. 6. pp. 420–433, 1976.
  22. A. Ahmadyfard and J. Kittler, “Region-Based Object Recognition: Pruning Multiple Representations and Hypotheses.,” in BMVC, 2000, pp. 1–10.
  23. A. Kostin, J. Kittler, and W. Christmas, “Object recognition by symmetrised graph matching using relaxation labelling with an inhibitory mechanism,” Pattern Recognit. Lett., vol. 26, no. 3, pp. 381–393, 2005.
  24. R. A. Hummel and S. W. Zucker, “On the Foundations of Relaxation Labeling Processes,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. PAMI-5, no. 3. pp. 267–287, 1983.
  25. A. Zohrevand, A. Ahmadyfard, A. Pouyan, and Z. Imani, “A SIFT based object recognition using contextual information,” in Intelligent Systems (ICIS), 2014 Iranian Conference on, 2014, pp. 1–4.
  26. F. Chevalier, J.-P. Domenger, J. Benois-Pineau, and M. Delest, “Retrieval of objects in video by similarity based on graph matching,” Pattern Recognit. Lett., vol. 28, no. 8, pp. 939–949, 2007.
  27. M. Amiri, A. Ahmadifard, and V. Abolghasemi, “A probabilistic framework for dense image registration using relaxation labelling,” in Signal Processing and Intelligent Systems (ICSPIS), International Conference of, 2016, pp. 1–5.
  28. B. Yousefi, S. M. Mirhassani, A. AhmadiFard, and M. Hosseini, “Hierarchical segmentation of urban satellite imagery,” Int. J. Appl. Earth Obs. Geoinf., vol. 30, pp. 158–166, 2014.


Object recognition, Probabilistic Relaxation Labeling, image descriptor, model image, scene image.