Abstract
Extraction and matching of discriminative feature points in images is an important problem in computer vision with applications in image classification, object recognition, mosaicing, automatic 3D reconstruction and stereo. Features are represented and matched via descriptors that must be invariant to small errors in the localization and scale of the extracted feature point, viewpoint changes, and other kinds of changes such as illumination, image compression and blur. While currently used feature descriptors are able to deal with many of such changes, they are not invariant to a generic monotonic change in the intensities, which occurs in many cases. Furthermore, their performance degrades rapidly with many image degradations such as blur and compression where the intensity transformation is non-linear. In this paper, we present a new feature descriptor that obtains invariance to a monotonic change in the intensity of the patch by looking at orders between certain pixels in the patch. An order change between pixels indicates a difference between the patches which is penalized. Summation of such penalties over carefully chosen pixel pairs that are stable to small errors in their localization and are independent of each other leads to a robust measure of change between two features. Promising results were obtained using this approach that show significant improvement over existing methods, especially in the case of illumination change, blur and JPEG compression where the intensity of the points changes from one image to the next.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Fabbri, R., da Fontoura Costa, L., Torelli, J.C., Bruno, O.M.: 2D Euclidean distance transform algorithms: A comparative survey. ACM Computer Survey (2008)
Mikolajczyk, K., Schmid, C.: An Affine Invariant Interest Point Detector. In: ECCV, pp. I-128 (2002)
Schaffalitzky, F., Zisserman, A.: Viewpoint Invariant Texture Matching and Wide Baseline Stereo. In: ICCV, pp. II, 636–643 (2001)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. In: IVC, September 10, 2004, pp. 761–767 (2004)
Tuytelaars, T., Van Gool, L.J.: Content-Based Image Retrieval Based on Local Affinely Invariant Regions. In: Huijsmans, D.P., Smeulders, A.W.M. (eds.) VISUAL 1999. LNCS, vol. 1614, pp. 493–500. Springer, Heidelberg (1999)
Tuytelaars, T., Van Gool, L.J.: Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions. BMVC (2000)
Kadir, T., Zisserman, A., Brady, M.: An Affine Invariant Salient Region Detector. In: ECCV, pp. I, 228–241 (2004)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.J.: A Comparison of Affine Region Detectors. IJCV 1-2, 43–72 (2005)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. IJCV 2, 91–110 (2004)
Mori, G., Belongie, S., Malik, J.: Efficient Shape Matching Using Shape Contexts. PAMI 11, 1832–1837 (2005)
Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. PAMI 10, 1615–1630 (2005)
Bay, H., Tuytelaars, T., Van Gool, L.J.: SURF: Speeded Up Robust Features. In: ECCV, pp. I, 404–417 (2006)
Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: CVPR, pp. II, 506–513 (2004)
Moreels, P., Perona, P.: Evaluation of Features Detectors and Descriptors Based on 3D Objects. IJCV, 263–284 (July 3, 2007)
Zabih, R., Woodfill, J.: Non-parametric local transforms fo computing visual correspondence. In: ECCV, pp. 151–158 (1994)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. PAMI, 971–987 (July 7, 2002)
Ahonen, T., Hadid, A., Pietikainen, M.: Face Description with Local Binary Patterns: Application to Face Recognition. PAMI, 2037–2041 (December 12, 2006)
Mittal, A., Ramesh, V.: An Intensity-augmented Ordinal Measure for Visual Correspondence. In: CVPR, pp. I: 849–856 (2006)
Gupta, R., Mittal, A.: Illumination and Affine- Invariant Point Matching using an Ordinal Approach. In: ICCV, pp. 1–8 (2007)
Lepetit, V., Fua, P.: Keypoint Recognition Using Randomized Trees. PAMI, 1465–1479 (September 9, 2006)
Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gupta, R., Mittal, A. (2008). SMD: A Locally Stable Monotonic Change Invariant Feature Descriptor. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88688-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-88688-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88685-3
Online ISBN: 978-3-540-88688-4
eBook Packages: Computer ScienceComputer Science (R0)