Regularity based descriptor computed from local image oscillations
Optics Express, Vol. 15, Issue 10, pp. 6140-6145 (2007)
http://dx.doi.org/10.1364/OE.15.006140
Acrobat PDF (877 KB)
Abstract
This work presents a novel local image descriptor based on the concept of pointwise signal regularity. Local image regions are extracted using either an interest point or an interest region detector, and discriminative feature vectors are constructed by uniformly sampling the pointwise Hölderian regularity around each region center. Regularity estimation is performed using local image oscillations, the most straightforward method directly derived from the definition of the Hölder exponent. Furthermore, estimating the Hölder exponent in this manner has proven to be superior, in most cases, when compared to wavelet based estimation as was shown in previous work. Our detector shows invariance to illumination change, JPEG compression, image rotation and scale change. Results show that the proposed descriptor is stable with respect to variations in imaging conditions, and reliable performance metrics prove it to be comparable and in some instances better than SIFT, the state-of-the-art in local descriptors.
© 2007 Optical Society of America
1. Introduction
4. D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int. J. Comput. Vision 2, 91–110 (2004). [CrossRef]
5. C. Schmid and K. Mikolajczyk, “A performance evaluation of local descriptors,” IEEE Trans. on Patt. Ana. and Mach. Int. 27, 1615–1630 (2005). [CrossRef]
2. Related work
5. C. Schmid and K. Mikolajczyk, “A performance evaluation of local descriptors,” IEEE Trans. on Patt. Ana. and Mach. Int. 27, 1615–1630 (2005). [CrossRef]
3. Hölder regularity
3.1. Estimating the Hölder exponent with oscillations
10. C. Tricot, Curves and Fractal Dimension (Springer-Verlag1995). [CrossRef]
4. Hölder descriptor
11. K. Mikolajczyk and C. Schmid, “Scale and affine invariant interest point detectors,” Int. J. Comput. Vision 1, 63–86 (2004). [CrossRef]
4. D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int. J. Comput. Vision 2, 91–110 (2004). [CrossRef]
5. Experimental results
12. Visual Geometry Group: http://www.robots.ox.ac.uk/ vgg/research/
5. C. Schmid and K. Mikolajczyk, “A performance evaluation of local descriptors,” IEEE Trans. on Patt. Ana. and Mach. Int. 27, 1615–1630 (2005). [CrossRef]
5. C. Schmid and K. Mikolajczyk, “A performance evaluation of local descriptors,” IEEE Trans. on Patt. Ana. and Mach. Int. 27, 1615–1630 (2005). [CrossRef]
12. Visual Geometry Group: http://www.robots.ox.ac.uk/ vgg/research/
6. Conclusions and future work
References and links
1. | H. P. Moravec, “Towards automatic visual obstacle avoidance,” in IJCAI, pp. 584 (1977). |
2. | L. Trujillo and G. Olague, “Synthesis of interest point detectors through genetic programming, ” in Proceedings from GECCO 2006, Mike Cattolico, eds., Vol.1, (ACM Press2006), pp. 887–894. |
3. | L. Trujillo and G. Olague, “Using Evolution to learn how to perform interest point detection,” in Proceedings from ICPR 2006, X.Y. Tang, et al., eds., Vol. 1, (IEEE2006), pp. 211–214. |
4. | D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int. J. Comput. Vision 2, 91–110 (2004). [CrossRef] |
5. | C. Schmid and K. Mikolajczyk, “A performance evaluation of local descriptors,” IEEE Trans. on Patt. Ana. and Mach. Int. 27, 1615–1630 (2005). [CrossRef] |
6. | K. Falconer, Fractal geometry Mathematical Foundations and Applications (Wiley, 1990). |
7. | J. Lévy Véhel, “Fractal Approaches in Signal Processing,” Fractals 3, 755–775 (1995). [CrossRef] |
8. | P. Legrand and J. Lévy Véhel, “Local regularity-based interpolation,” in WAVELET X, Part of SPIE’s Symposium on Optical Science and Technology, SPIE 5207 (2003). |
9. | P. Legrand, “Debruitage et interpolation par analyse de la regularite Hölderienne. Application a la modelisation du frottement pneumatique-chaussee,” P.h.D. thesis, Université de Nantes (2004). |
10. | C. Tricot, Curves and Fractal Dimension (Springer-Verlag1995). [CrossRef] |
11. | K. Mikolajczyk and C. Schmid, “Scale and affine invariant interest point detectors,” Int. J. Comput. Vision 1, 63–86 (2004). [CrossRef] |
12. | Visual Geometry Group: http://www.robots.ox.ac.uk/ vgg/research/ |
OCIS Codes
(100.5010) Image processing : Pattern recognition
(100.5760) Image processing : Rotation-invariant pattern recognition
(110.2960) Imaging systems : Image analysis
ToC Category:
Image Processing
History
Original Manuscript: September 18, 2006
Revised Manuscript: December 14, 2006
Manuscript Accepted: February 26, 2007
Published: May 3, 2007
Citation
Leonardo Trujillo, Gustavo Olague, Pierrick Legrand, and Evelyne Lutton, "Regularity based descriptor computed from local image oscillations," Opt. Express 15, 6140-6145 (2007)
http://www.opticsinfobase.org/oe/abstract.cfm?URI=oe-15-10-6140
Sort: Year | Journal | Reset
References
- H. P. Moravec, "Towards automatic visual obstacle avoidance," in IJCAI, pp. 584 (1977).
- L. Trujillo and G. Olague, "Synthesis of interest point detectors through genetic programming, " in Proceedings from GECCO 2006, M. Cattolico, ed., (ACM Press 2006), Vol. 1, pp. 887-894.
- L. Trujillo and G. Olague, "Using Evolution to learn how to perform interest point detection," in Proceedings from ICPR 2006, X.Y. Tang et al., eds., (IEEE 2006), Vol. 1, pp. 211-214.
- D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int. J. Comput. Vision 2, 91-110 (2004). [CrossRef]
- C. Schmid and K. Mikolajczyk, "A performance evaluation of local descriptors," IEEE Transactions on PatternAnalysis and Machine Intelligence. 27, 1615-1630 (2005). [CrossRef]
- K. Falconer, Fractal geometry, Mathematical Foundations and Applications (Wiley, 1990).
- J. Lévy Véhel, "Fractal approaches in Signal Processing," Fractals 3, 755-775 (1995). [CrossRef]
- P. Legrand and J. Lévy Véhel, "Local regularity-based interpolation," in WAVELET X, Part of SPIE’s Symposium on Optical Science and Technology, SPIE 5207 (2003).
- P. Legrand, "Debruitage et interpolation par analyse de la regularite Hölderienne. Application a la modelisation du frottement pneumatique-chaussee," Ph. D. thesis, Université de Nantes (2004).
- C. Tricot, Curves and Fractal Dimension (Springer-Verlag 1995). [CrossRef]
- K. Mikolajczyk and C. Schmid, "Scale and affine invariant interest point detectors," Int. J. Comput. Vision 1, 63-86 (2004). [CrossRef]
- Visual Geometry Group: http://www.robots.ox.ac.uk/ vgg/research/
Cited By |
Alert me when this paper is cited |
OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.
« Previous Article | Next Article »
OSA is a member of CrossRef.