DETECTORS OF EXTREMAL KEY POINTS ON IMAGES
Abstract
Extremal key-point detectors are presented to describe, analyze and compare images by local descriptors that are determined in neighborhoods of the detected key-points. The proposed detectors select key-points, providing local extremal values of the function that characterizes local properties of the original image at each pixel. The majority of commonly used detecting algorithms are looking for key-points in another way. They mark a pixel as a key-point if the value of the functioncriterion at this pixel exceeds a predetermined threshold value. The remaining known algorithms find key-points that are the local extremal values of the functions defined on gradient transforms of the image. One of the drawbacks of the known detectors (in addition to the use of learning procedures expensive in the computational sense) is a non-uniform distribution of key-points on the image. Often large image areas may be left with no key-points, making their detection or recognition impossible. The proposed extremal detectors allow one in many cases to avoid the appearance of image areas not filled with key-points.
About the Author
B. A. Zalesky
United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk
Belarus
Belarus
D. Sc. (Physics and Mathematics), Head of the Laboratory
6, Surganov Str., 220012
References
1. Lowe D. Object recognition from local scale invariant features. Proceedings of the 7th IEEE International Conference on Computer Vision ICCV, Corfu, 1999, pp. 1150–1157. doi.org/10.1109/iccv.1999.790410
2. Dalah N., Triggs B. Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR’05, San Diego, 2005, vol. 1, pp. 886–893. doi.org/10.1109/cvpr.2005.177
3. Bay H., Tuytelaars T., Van Gool L. Surf: Speeded up robust features. Proceedings of the 9th European Conference on Computer Vision ECCV, Graz, 2006, pp. 404–417. doi.org/10.1007/11744023_32
4. Rosten E., Porter R., Drummond T. Faster and better: a machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, vol. 32, no. 1, pp. 105–119. doi.org/10.1109/tpami.2008.275
5. Agrawal M., Konolige K., Blas M. R. CenSurE: Center surround extremas for realtime feature detection and matching. Lecture Notes in Computer Science, 2008, vol. 5305, pp. 102–115. doi.org/10.1007/978-3-540-88693-8_8
6. Leutenegger S., Chli M., Siegwart R. Y. BRISK: Binary Robust invariant scalable keypoints. Proceedings of the 13th IEEE International Conference on Computer Vision ICCV, Barcelona, 2011, pp. 2548–2555. doi.org/10.1109/iccv.2011.6126542
7. Alcantarilla P., Bartoli A., Davison J. KAZE Features. Proceedings of the 12th European Conference on Computer Vision ECCV. Firenze, 2012, pp. 214–227. doi.org/10.1007/978-3-642-33783-3_16
8. Alcantarilla P., Nuevo J., Bartoli A. Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces. Proceedings of the 24th British Machine Vision Conference BMVC. Bristol, 2013. doi.org/10.5244/C.27.13
9. Schmidt A., Kraft M., Fularz M., Domagała Z. Comparative Assessment of Point Feature Detectors and Descriptors in the Context of Robot Navigation. Journal of Automation, Mobile Robotics & Intelligent Systems, 2013, vol. 7, no. 1, pp. 11–20.
10. Viola P., Jones M. J. Robust real-time face detection. International Journal of Computer Vision, 2004, vol. 57, no. 2, pp. 137–154. doi.org/10.1023/b:visi.0000013087.49260.fb
Review
Views: 718
Email this article 