Publication: A probabilistic neural network for attribute selection in stereovision matching
Loading...
Official URL
Full text at PDC
Publication Date
2002-10
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer-Verlag
Citations
Exportar
Abstract
The key step in stereovision is image matching. This is carried out on the basis of selecting features, edge points, edge segments, regions, corners, etc. Once the features have been selected, a set of attributes (properties) for matching is chosen. This is a key issue in stereovision matching. This paper presents an approach for attribute selection in stereovision matching tasks based on a Probabilistic Neural Network, which allows the computation of a mean vector and a covariance matrix from which the relative importance of attributes for matching and the attribute interdependence can be derived. This is possible because the matching problem focuses on a pattern classification problem. The performance of the method is verified with a set of stereovision images and the results contrasted with a classical attribute selection method and also with the relevance concept.
Description
© 2002 Springer-Verlag London Limited.
Part of the work has been performed under project CICYT TAP94-0832-C02-01. The constructive recommendations provided by the reviewers are also gratefully acknowledged.
UCM subjects
Unesco subjects
Keywords
Citation
1. Marr D, Poggio TA (1979) Computational theory of human stereovision. Proc Royal Society of London B207: 301–328
2. Medioni G, Nevatia R (1985) Segment based stereo matching. Computer Vision, Graphics, and Image Processing 31: 2–18
3. Pollard SB, Mayhew JEW, Frisby JP (1981) PMF: A stereo correspondence algorithm using a disparity gradient limit. Perception 14: 449–470
4. Cruz JM, Pajares G, Aranda J (1995) A neural network approach to the stereovision correspondence problem by unsupervised learning. Neural Networks 8(5):805–813
5. Hunter A (2000) Feature selection using probabilistic neural networks. Neural Computing and Applications 9: 124-132
6. Specht DF (1990) Probabilistic neural networks. Neural Networks 3(1): 109–118
7. Traven HGC (1991) A neural network approach to statistical pattern classification by semiparametric estimation of probability density function. IEEE Trans Neural Networks 2: 366–377
8. Pajares G (1995) Estrategia de Solución al Problema de la Correspondencia en Vision Estereoscópica por la Jerarquía Metodológica y la Integración de Criterios, PhD thesis, Dpto. Informática y Automática, Facultad Ciencias UNED: Madrid
9. Pajares G, Cruz JM, López JA (1998) Pattern recognition learning applied to stereovision matching. In: Amin A, Dori D, Pudil P, Freeman H, editors, Advances in Pattern Recognition. Springer-Verlag, Berlin, 997–1004
10. Duda RO, Hart PE, Stork, DG (2001) Pattern Classification and Scene Analysis. Wiley, New York
11. Maravall D (1993) Reconocimiento de Formas y Visión Artificial. RA-MA, Madrid
12. Huertas A, Medioni G (1986) Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks. IEEE Trans Pattern Anal Machine Intell 8(5): 651–664
13. Leu JG, Yau HL (1991) Detecting the dislocations in metal crystals from microscopic images. Pattern Recognition 24(1): 41–56
14. Krotkov EP (1989) Active Computer Vision by Cooperative Focus and Stereo. Springer-Verlag, Berlin
15. Tanaka S, Kak, AC (1990) A rule-based approach to binocular stereopsis. In: Jain RC, Jain AK, editors, Analysis and Interpretation of Range Images.Springer-Verlag, Berlin
16. Nevatia R, Babu KR (1980) Linear feature extraction and description. Computer Vision, Graphics and Image Processing 13: 257–269
17. Lew MS, Huang TS, Wong K (1994) Learning and feature selection in stereo matching. IEEE Trans Pattern Anal Machine Intell 16(9): 869–881
18. Wang H, Bell D, Murtagh F (1999) Axiomatic approach to feature subset selection based on relevance. IEEE Trans Pattern Anal Machine Intell 21(3): 271–277
19. Gonzalez RC, Woods RE (1993) Digital Image Processing, Addison-Wesley, Reading, MA
20. Pajares G, Cruz JM (2001) Local stereovision matching through the ADALINE neural network. Pattern Recognition Letters 22: 1457–1473
21. Pajares G, Cruz JM (2002) The non-parametric Parzen’s Window in stereo vision matching. IEEE Trans Sys, Man Cybernetics 32(2)