New paradigm of learnable computer vision algorithms based on the representational MDL principle

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 7696, Issue , 2010, Pages

  Potapov, Alexey S ^a   Malyshev, Igor A ^a   Puysha, Alexander E ^a   Averkin, Anton N ^b  

^a VAVILOV STATE OPTICAL INSTITUTE   (Russian Federation)

^b ITMO UNIVERSITY   (Russian Federation)

Author keywords

Feature; Image; Information theoretic; Learning; MDL; Representation; Segmentation

Indexed keywords

COMPUTER VISION ALGORITHMS; COMPUTER VISION SYSTEM; FEATURE IMAGES; IMAGE ANALYSIS ALGORITHMS; IMAGE REPRESENTATIONS; IMAGE SAMPLES; LOCAL FEATURE; MACHINE LEARNING METHODS; MDL PRINCIPLE; MINIMUM DESCRIPTION LENGTH PRINCIPLE; OBJECT DOMAINS; OPTIMAL MODEL; OPTIMIZATION CRITERIA; SINGLE IMAGES;

AUTOMATIC TARGET RECOGNITION; COMPUTATIONAL METHODS; COMPUTER VISION; IMAGE ANALYSIS; IMAGE SEGMENTATION; INFORMATION THEORY; LEARNING SYSTEMS; OPTICAL DATA PROCESSING; OPTIMIZATION; PATTERN RECOGNITION SYSTEMS;

LEARNING ALGORITHMS;

EID: 77953786943     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.849532     Document Type: Conference Paper

References (12)

1. Piater, J. H. and Grupen, R. A., "Distinctive features should be learned," Proc. IEEE Int'l Workshop on Biologically Motivated Computer Vision, Springer-Verlag, LNCS 1811, 52-61 (2000).
2. Sim, R. and Dudek, G., "Learning Generative Models of Invariant Features," Proc. IEEE/RSJ Conf. on Intelligent Robots and Systems, IROS, Sendai, Japan, vol. 4, 3481-3488 (2004).
3. Lowe, D.G., "Distinctive Image Features from Scale-Invariant Keypoints," Int. J. of Computer Vision, 60(2), 91-110 (2004).
4. Kopparapu, S.K. and Desai, U.B., "Bayesian Approach to Image Interpretation," The Springer Int. Series in Engineering and Computer Science 616, 127 pages (2001).
5. Li, M. and Vitanyi, P., "Philosophical Issues in Kolmogorov complexity," Proc. ICALP, invited lect., 1-15 (1992).
6. Rissanen, J.J., "Modeling by the shortest data description," Automatica-J.IFAC 14, 465-471 (1978).
7. nd Asian Conf. on Computer Vision, Singapore, 45-52 (1995).
8. th European Conf. on Computer Vision. Graz, Austria, vol. 3951, 404-417 (2006).
9. Solomonoff, R., "Does Algorithmic Probability Solve the Problem of Induction?" Oxbridge Research, P.O.B. 391887, Cambridge, Mass. 02139. 1997.
10. Hyväninen, A., "Survey on Independent Component Analysis," Neural Computing Surveys 2, 94-128 (1999).
11. Pineda, I., Gokcen, I., Buckles, B., "Image Feature Set for Correspondence Mappings," Int'l J. of High Performance Computing Applications, 16(3), 273-283 (2002).
12. Ke, Y. and Sukthankar, R., "PCA-SIFT: A More Distinctive Representation for Local Image Descriptors," Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 506-513 (2004).