Multiobjective design of operators that detect points of interest in images

ABSTRACT

In this paper, a multiobjective (MO) learning approach to image feature extraction is described, where Pareto-optimal interest point (IP) detectors are synthesized using genetic programming (GP). IPs are image pixels that are unique, robust to changes during image acquisition, and convey highly descriptive information. Detecting such features is ubiquitous to many vision applications, e.g. object recognition, image indexing, stereo vision, and content based image retrieval. In this work, candidate IP operators are automatically synthesized by the GP process using simple image operations and arithmetic functions. Three experimental optimization criteria are considered: 1) the repeatability rate; 2) the amount of global separability between IPs; and 3) the information content captured by the set of detected IPs. The MO-GP search considers Pareto dominance relations between candidate operators, a perspective that has not been contemplated in previous research devoted to this problem. The experimental results suggest that IP detection is an illposed problem for which a single globally optimum solution does not exist. We conclude that the evolved operators outperform and dominate, in the Pareto sense, all previously man-made designs.

REFERENCES

• 1: H Asada , M Brady, The curvature primal sketch, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8 n.1, p.2-14, Jan. 1986 [doi>10.1109/TPAMI.1986.4767747]
• 2: P. R. Beaudet. Rotational invariant image operators. In Proceedings of the 4th International Joint Conference on Pattern Recognition (ICPR 1978),Tokyo, Japan, pages 579--583, 1978.
• 3: Y. Caron , P. Makris , N. Vincent, Use of power law models in detecting region of interest, Pattern Recognition, v.40 n.9, p.2521-2529, September, 2007 [doi>10.1016/j.patcog.2007.01.004]
• 4: Andrew J. Davison , Ian D. Reid , Nicholas D. Molton , Olivier Stasse, MonoSLAM: Real-Time Single Camera SLAM, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.29 n.6, p.1052-1067, June 2007 [doi>10.1109/TPAMI.2007.1049]
• 5: W. Förstner and E. Gülch. A fast operator for detection and precise location of distinct points, corners and centres of circular features. In ISPRS Intercommission Conference on fast processing of photogrammetric data, pages 149--155, 1987.
• 6: C. Harris and M. Stephens. A combined corner and edge detector. In Proceedings from the Fourth Alvey Vision Conference, volume 15, pages 147--151, 1988.
• 7: C. S. Kenney , M. Zuliani , B. S. Manjunath, An Axiomatic Approach to Corner Detection, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1, p.191-197, June 20-26, 2005 [doi>10.1109/CVPR.2005.68]
• 8: L. Kitchen and A. Rosenfeld. Gray-level corner detection. Pattern Recognition Letters, 1:95--102, December 1982.
• 9: J J Koenderink , A J van Doom, Representation of local geometry in the visual system, Biological Cybernetics, v.55 n.6, p.367-375, March 1987 [doi>10.1007/BF00318371]
• 10: Ivan Laptev , Tony Lindeberg, Space-time Interest Points, Proceedings of the Ninth IEEE International Conference on Computer Vision, p.432, October 13-16, 2003
• 11: Vincent Lepetit , Pascal Fua, Keypoint Recognition Using Randomized Trees, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.9, p.1465-1479, September 2006 [doi>10.1109/TPAMI.2006.188]
• 12: Qi Li , Jieping Ye , Chandra Kambhamettu, Interest point detection using imbalance oriented selection, Pattern Recognition, v.41 n.2, p.672-688, February, 2008 [doi>10.1016/j.patcog.2007.06.020]
• 13: David G. Lowe, Object Recognition from Local Scale-Invariant Features, Proceedings of the International Conference on Computer Vision-Volume 2, p.1150, September 20-25, 1999
• 14: Krystian Mikolajczyk , Cordelia Schmid, A Performance Evaluation of Local Descriptors, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.27 n.10, p.1615-1630, October 2005 [doi>10.1109/TPAMI.2005.188]
• 15: K. Mikolajczyk , T. Tuytelaars , C. Schmid , A. Zisserman , J. Matas , F. Schaffalitzky , T. Kadir , L. Van Gool, A Comparison of Affine Region Detectors, International Journal of Computer Vision, v.65 n.1-2, p.43-72, November 2005 [doi>10.1007/s11263-005-3848-x]
• 16: H. P. Moravec. Towards automatic visual obstacle avoidance. In IJCAI, page 584, 1977.
• 17: Gustavo Olague , Benjamín Hernández, A new accurate and flexible model based multi-corner detector for measurement and recognition, Pattern Recognition Letters, v.26 n.1, p.27-41, 1 January 2005 [doi>10.1016/j.patrec.2004.08.026]
• 18: V. Pareto. Cours D'Economie Politique. Rouge, Lausanne, 1896.
• 19: B. Platel, E. Balmachnova, L. Florack, and B. M. ter Haar Romeny. Top-points as interest points for image matching. In A. Leonardis et al., editors, Proceedings from ECCV 2006, 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006, Part I, volume 3951 of Lecture Notes in Computer Science, pages 418--429. Springer, 2006.
• 20: Ahmed Rebai , Alexis Joly , Nozha Boujemaa, Interpretability based interest points detection, Proceedings of the 6th ACM international conference on Image and video retrieval, p.33-40, July 09-11, 2007, Amsterdam, The Netherlands [doi>10.1145/1282280.1282285]
• 21: Karl Rohr, Recognizing corners by fitting parametric models, International Journal of Computer Vision, v.9 n.3, p.213-230, Dec. 1992 [doi>10.1007/BF00133702]
• 22: Cordelia Schmid , Roger Mohr , Christian Bauckhage, Evaluation of Interest Point Detectors, International Journal of Computer Vision, v.37 n.2, p.151-172, June 2000 [doi>10.1023/A:1008199403446]
• 23: J. Shi and C. Tomasi. Good features to track. In Proceedings of the 1994 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'94), June 1994, Seattle, WA, USA, pages 593--600. IEEE Computer Society, 1994.
• 24: P. Tissainayagam and D. Suter. Assessing the performance of corner detectors for point feature tracking applications. Image Vision Comput., 22(8):663--679, 2004.
• 25: Leonardo Trujillo , Gustavo Olague, Synthesis of interest point detectors through genetic programming, Proceedings of the 8th annual conference on Genetic and evolutionary computation, July 08-12, 2006, Seattle, Washington, USA [doi>10.1145/1143997.1144151]
• 26: Leonardo Trujillo , Gustavo Olague, Using Evolution to Learn How to Perform Interest Point Detection, Proceedings of the 18th International Conference on Pattern Recognition, p.211-214, August 20-24, 2006 [doi>10.1109/ICPR.2006.1153]
• 27: Joost van de Weijer , Theo Gevers , Andrew D. Bagdanov, Boosting Color Saliency in Image Feature Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.1, p.150-156, January 2006 [doi>10.1109/TPAMI.2006.3]
• 28: H. Wang and J. Brady. Corner detection for 3d vision using array processors. In Proceedings from BARNAIMAGE 91, Barcelona, Spain, Secaucus, NJ, USA, 1991. Springer-Verlag.
• 29: Gehua Yang , Charles V. Stewart , Michal Sofka , Chia-Ling Tsai, Registration of Challenging Image Pairs: Initialization, Estimation, and Decision, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.29 n.11, p.1973-1989, November 2007 [doi>10.1109/TPAMI.2007.1116]
• 30: E. Zitzler, M. Laumanns, and L. Thiele. Spea2: Improving the strength pareto evolutionary algorithm for multiobjective optimization. In Evolutionary Methods for Design, Optimisation, and Control, pages 19--26, 2002.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.7 Feature Measurement
          Subjects: Feature representation

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.2 Automatic Programming
          Subjects: Program synthesis
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.7 Feature Measurement
          Subjects: Invariants

General Terms:
Algorithms, Experimentation, Performance, Theory

Keywords:
interest point detection, multiobjective optimization