Supervised Scale-Invariant Segmentation (and Detection)
The scale-invariant detection of image structure has been a topic of study within computer vision and image analysis since long. To date, Lindeberg’s scale selection method has probably been the most fruitful and successful approach to this problem. It provides a general technique to cope with the detection of structures over scale that can be successfully expressed in terms of Gaussian differential operators. Any detection or segmentation task would potentially benefit from a similar approach to deal with scale. For many of the real-world image structures of interest, however, it will often be impossible to explicitly design or handcraft an operator that is capable of detecting them in a sensitive and specific way. In this paper, we present an approach to the scale-selection problem in which the construction of the detector is driven by supervised learning techniques. The resulting classification method is designed so as to achieve scale-invariance and may be thought of as a supervised version of Lindeberg’s classical scheme.
KeywordsScale selection scale-invariance image segmentation detection learning classification
Unable to display preview. Download preview PDF.
- 3.Brodatz, P.: Textures: A Photographic Album for Artists & Designers. Dover, New York (1966)Google Scholar
- 5.Duin, R., Tax, D.: Classifier conditional posterior probabilities. In: Advances in Pattern Recognition, pp. 611–619 (1998)Google Scholar
- 15.Kokkinos, I., Yuille, A.: Scale invariance without scale selection. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–8. IEEE, Los Alamitos (2008)Google Scholar
- 16.Leung, M., Peterson, A.: Scale and rotation invariant texture classification. In: The 26th Asilomar Conference on Signals, Systems and Computers, pp. 461–465 (1992)Google Scholar
- 23.Papageorgiou, C., Oren, M., Poggio, T.: A general framework for object detection. In: Sixth International Conference on Computer Vision, pp. 555–562. IEEE, Los Alamitos (2002)Google Scholar
- 24.Platel, B., Kanters, F., Florack, L., Balmachnova, E.: Using multiscale top points in image matching. In: International Conference on Image Processing, ICIP 2004, vol. 1, pp. 389–392. IEEE, Los Alamitos (2005)Google Scholar
- 25.Pun, C., Lee, M.: Log-polar wavelet energy signatures for rotation and scale invariant texture classification. IEEE Trans. PAMI, 590–603 (2003)Google Scholar
- 26.Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object detection. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 1, pp. 503–510. IEEE, Los Alamitos (2005)Google Scholar