Evaluation of Interest Point Detectors in Presence of Noise

Full Text (PDF, 1288KB), PP.26-33

Views: 0 Downloads: 0


Adrian Ziomek 1,* Mariusz Oszust 1

1. Department of Computer and Control Engineering, Rzeszow University of Technology Wincentego Pola 2, 35-959 Rzeszow, Poland

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2016.03.03

Received: 1 Jul. 2015 / Revised: 25 Sep. 2015 / Accepted: 22 Dec. 2015 / Published: 8 Mar. 2016

Index Terms

Keypoint, interest point detectors, distortions, noise, repeatability, evaluation, pattern recognition


Detection of repeatable keypoints is often one of the first steps leading to obtain a solution able to recognise objects on images. Such objects are characterised by content of image patches indicated by keypoints. A given image patch is worth being described and processed in further steps, if the interest point inside of it can be found despite different image transformations or distortions. Therefore, it is important to compare keypoint detection techniques using image datasets that contain transformed or noisy images. Since most of detector evaluations rely on small datasets or are focused on a specific application of compared techniques, in this paper two large datasets which cover typical transformations, as well as challenging distortions that can occur while image processing, are used. The first dataset contains 200,000 transformed images, and it has been prepared for the purpose of this study. The second dataset, TID2013, is widely used for perceptual image quality assessment; it contains 3,000 images with 24 distortions. Finally, interest point detectors are evaluated on four datasets, and repeatability score and time of detection are used as measures of their performance.

Cite This Paper

Adrian Ziomek, Mariusz Oszust, "Evaluation of Interest Point Detectors in Presence of Noise", International Journal of Intelligent Systems and Applications(IJISA), Vol.8, No.3, pp.26-33, 2016. DOI:10.5815/ijisa.2016.03.03


[1]Ş. Işık, “A comparative evaluation of well-known feature detectors and descriptors,” International Journal of Applied Mathematics, Electronics and Computers, vol. 3, no. 1, 2015, pp. 1-6. doi: 10.18100/ijamec.60004.
[2]K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, and L. Van Gool, “A comparison of affine region detectors,” Int. J. Comput. Vision, vol. 65, no. 1-2, 2005, pp. 43-72. doi: 10.1007/s11263-005-3848-x.
[3]J. Heinly, E. Dunn, and J. M. Frahm, “Comparative evaluation of binary features,” European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, 2012, Springer, pp. 759-773. doi: 10.1007/978-3-642-33709-3_54.
[4]V. G. Spasova, “Experimental evaluation of keypoints detector and descriptor algorithms for indoors person localization,” Annual J. Electronics, vol. 8, 2014, pp. 85-87.
[5]T. Dickscheid and W. F?rstner, “Evaluating the suitability of feature detectors for automatic image orientation systems,” Computer Vision Systems, 2009, Springer Berlin Heidelberg, pp. 305-314. doi: 10.1007/978-3-642-04667-4_31.
[6]J. Bauer, N. Sunderhauf, and P. Protzel, “Comparing several implementations of two recently published feature detectors,” Proc. of the International Conference on Intelligent and Autonomous Systems, vol. 6, p. 1, 2007, pp. 143-148. doi: 10.3182/20070903-3-FR-2921.00027.
[7]O. Miksik and K. Mikolajczyk, “Evaluation of local detectors and descriptors for fast feature matching,” 21st International Conference on Pattern Recognition (ICPR), 2012, IEEE, pp. 2681-2684.
[8]V. Rodehorst and A. Koschan, “Comparison and evaluation of feature point detectors,” Proc. 5th International Symposium Turkish-German Joint Geodetic “Days Geodesy and Geoinformation in the Service of our Daily Life,” Berlin, Germany, 2006.
[9]C. Schmid, R. Mohr, and C. Bauckhage, “Evaluation of interest point detectors,” Int. J. Comput. Vision, vol. 37, no. 2, 2000, pp. 151–172. doi:10.1023/A:1008199403446.
[10]F. A. Khalifa, N. A. Semary, H.M. El-Sayed, and M. M. Hadhoud, ”Local detectors and descriptors for object class recognition,” I. J. Intelligent Systems and Applications, vol. 7, no. 10, 2015, pp. 12-18. doi: 10.5815/ijisa.2015.10.02.
[11]S. Filipe and L. A. Alexandre, “A comparative evaluation of 3D keypoint detectors in a RGB-D object dataset,” 9th International Conference on Computer Vision Theory and Applications, 2014, pp. 476-483. doi: 10.5220/0004679904760483.
[12]F. Tombari, S. Salti, and L. Di Stefano, “Performance evaluation of 3D keypoint detectors,” Int. J. Comput. Vision, vol. 102, no. 1-3, 2013, pp. 198-220. doi: 10.1007/s11263-012-0545-4.
[13]P. Moreels and P. Perona, “Evaluation of features detectors and descriptors based on 3D objects,” Int. J. Comput. Vision, vol. 73, no. 3, 2007, pp. 263-284. doi: 10.1007/s11263-006-9967-1.
[14]H. Moravec, “Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover,” Tech Report CMU-RI-TR-3, Carnegie Mellon University Technical Report, 1980.
[15]C. Harris and M. Stephens, “A combined corner and edge detector,” In Proc. of Fourth Alvey Vision Conference, vol. 15, 1988, pp. 147-151.
[16]C. Tomasi and T. Kanade, “Detection and tracking of point features,” Tech Report CMU-CS-91-132, Carnegie Mellon University Technical Report, 1991.
[17]J. Shi and C. Tomasi, “Good features to track,” Computer Vision and Pattern Recognition, Proceedings, IEEE, 1994, pp. 593 – 600, doi: 10.1109/CVPR.1994.323794.
[18]L. Kitchen and A. Rosenfeld, “Gray-level corner detection,” Pat. Rec. Let., vol. 1, no. 2, 1982, pp. 95–102. doi: 10.1016/0167-8655(82)90020-4.
[19]E. Rosten, R. Porter, and T. Drummond, “Faster and better: A machine learning approach to corner detection,” Pat. Anal. Mach.Intell., IEEE Trans. on, vol. 32, no. 1, 2010, pp. 105-119. doi: 10.1109/TPAMI.2008.275.
[20]D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vision, vol. 60, no. 2, 2004, pp. 91-110. doi: 10.1023/B:VISI.0000029664.99615.94.
[21]H. Bay, T. Tuytelaars, and L. Van Gool, “Surf: Speeded up robust features,” European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, 2006, Springer, pp. 404-417. doi: 10.1007/11744023_32.
[22]Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” Image Proc., IEEE Transactions on, vol. 13, no. 4, 2004, pp. 600-612. doi: 10.1109/TIP.2003.819861.
[23]D. M. Chandler, “Seven challenges in image quality assessment: Past, present, and future research,” ISRN Signal Processing, vol. 2013, Article ID 905685, 53 pages, 2013. doi:10.1155/2013/905685.
[24]N. Ponomarenko, L. Jin, O. Ieremeiev, V Lukin, K. Egiazarian, J. Astola, and C. C. J. Kuo, “Image database TID2013: Peculiarities, results and perspectives,” Sig. Proc.: Image Com., vol. 30, 2015, pp. 57-77. doi: 10.1016/j.image.2014.10.009.
[25]M. J. Huiskes and M. S. Lew (2008), “The MIR Flickr retrieval evaluation,” ACM International Conference on Multimedia Information Retrieval, 2008, pp. 39-43. doi: 10.1145/1460096.1460104.
[26]P. Abeles, “Speeding up SURF,” Advances in Visual Computing - 9th International Symposium, LNCS, vol. 8034, 2013, Springer, pp. 454-464. doi: 10.1007/978-3-642-41939-3_44.