Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation
Abstract
We introduce a novel framework for automatic detection of repeated patterns in real images. The novelty of our work is to formulate the extraction of an underlying deformed lattice as a spatial, multi-target tracking problem using a new and efficient Mean-Shift Belief Propagation (MSBP) method. Compared to existing work, our approach has multiple advantages, including: 1) incorporating higher order constraints early-on to propose highly plausible lattice points; 2) growing a lattice in multiple directions simultaneously instead of one at a time sequentially; and 3) achieving more efficient and more accurate performance than state-of-the-art algorithms. These advantages are demonstrated by quantitative experimental results on a diverse set of real world photos.
Keywords
Belief Propagation Interest Point Real Image Markov Random Field Texture ElementPreview
Unable to display preview. Download preview PDF.
Supplementary material
References
- 1.Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston (1950)Google Scholar
- 2.Julesz, B.: Visual pattern discrimination. IRE Transactions on Information Theory 8(2), 84–92 (1962)CrossRefGoogle Scholar
- 3.Coxeter, H.: Introduction to Geometry, 2nd edn. Wiley, New York (1980)zbMATHGoogle Scholar
- 4.Weyl, H.: Symmetry. Princeton University Press, Princeton (1952)CrossRefzbMATHGoogle Scholar
- 5.Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: cue integration in image segmentation. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 918–925 (1999)Google Scholar
- 6.Forsyth, D.: Shape from texture without boundaries. In: 7th European Conference on Computer Vision, pp. 43–66 (2002)Google Scholar
- 7.Liu, Y., Lin, W.C., Hays, J.: Near-regular texture analysis and manipulation. ACM Transactions on Graphics 23(3), 368–376 (2004)CrossRefGoogle Scholar
- 8.Ghanem, B., Ahuja, N.: Phase based modelling of dynamic textures. In: IEEE 11th International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
- 9.Schattschneider, D.: The plane symmetry groups: their recognition and notation. American Mathematical Monthly 85, 439–450 (1978)MathSciNetCrossRefzbMATHGoogle Scholar
- 10.Liu, Y., Collins, R.T., Tsin, Y.: A computational model for periodic pattern perception based on frieze and wallpaper groups. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(3), 354–371 (2004)CrossRefGoogle Scholar
- 11.Liu, Y., Tsin, Y., Lin, W.C.: The promise and perils of near-regular texture. International Journal of Computer Vision 62(1-2), 145–159 (2005)CrossRefGoogle Scholar
- 12.Hays, J., Leordeanu, M., Efros, A., Liu, Y.: Discovering texture regularity as a higher-order correspondence problem. In: 9th European Conference on Computer Vision (2006)Google Scholar
- 13.Lin, W.C., Liu, Y.: Tracking Dynamic Near-regular Textures under Occlusions and Rapid Movements. In: 9th European Conference on Computer Vision (2006)Google Scholar
- 14.Lin, W.-C., Liu, Y.: A lattice-based MRF model for dynamic near-regular texture tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(5), 777–792 (2007)CrossRefGoogle Scholar
- 15.Park, M., Liu, Y., Collins, R.T.: Efficient Mean Shift Belief Propagation for Vision Tracking. In: Computer Vision and Pattern Recognition, Anchorage, Alaska (2008)Google Scholar
- 16.Shi, J., Tomasi, C.: Good features to track. In: Computer Vision and Pattern Recognition, 1994, pp. 593–600 (1994)Google Scholar
- 17.Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(4), 509–522 (2002)CrossRefGoogle Scholar