×

Coarse-to-fine planar object identification using invariant curve features and \(B\)-spline modeling. (English) Zbl 1183.68532

Summary: The paper presents a hybrid algorithm for coarse-to-fine-matching of affine-invariant object features and B-spline object curves, and simultaneous estimation of transformation parameters. For coarse-matching, two dissimilar measures are exploited by using the significant corners of object boundaries to remove candidate objects with large dissimilarity to a target object. For fine-matching, a robust point interpolation approach and a simple gradient-based algorithm are applied to B-spline object curves under MMSE criterion. The combination of coarse and fine-matching steps reduces the computational cost without degrading the matching accuracy. The proposed algorithm is evaluated using affine transformed objects.

MSC:

68T10 Pattern recognition, speech recognition
65D07 Numerical computation using splines
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Sullivan, G., Visual interpretation of known objects in constrained scenes, Philos. Trans. Roy. Soc. Lond. B., 337, 361-370 (1992)
[2] Wu, X.; Bhanu, B., Gabor wavelet representation for 3-D object recognition, IEEE Trans. Image Process., 6, 1, 47-64 (1997)
[3] Nelson, R. C.; Aloimonos, J., Obstacle avoidance using flow field divergence, IEEE Trans. Pattern Anal. Mach. Intell., 11, 10, 1102-1106 (1989)
[4] Mailloux, G. E.; Langlois, F.; Simard, P. L.; Bertrand, M., Restoration of the velocity field of the heart from two-dimensional echocardiograms, IEEE Trans. Med. Imaging, 8, 2, 143-153 (1989)
[5] Gee, A.; Cipolla, R., Fast visual tracking by temporal consensus, Image Vision Comput., 14, 2, 105-114 (1994)
[6] Pavlovic, V. I.; Sharma, R.; Huang, T. S., Visual interpretation of hand gestures for human-computer interpretationa review, IEEE Trans. Pattern Anal. Mach. Intell., 19, 667-695 (1997)
[7] Manjunath, B. S.; Ma, W. A., Texture features for browsing and retrieval of image data, IEEE Trans. Pattern Anal. Mach. Intell., 18, 837-842 (1997)
[8] Musmann, H. G.; Hotter, M.; Ostermann, J., Object-oriented analysis-synthesis coding of moving images, Signal Process. Image Commun., 1, 2, 117-138 (1989)
[9] Chellappa, R.; Girod, B.; Munson, D. C.; Tekalp, M.; Vetterli, M., The past, present and future of image and multidimensional signal processing, IEEE SP Mag., 15, 2, 21-58 (1998)
[10] Torres, L.; Kunt, M., Video CodingThe 2nd Generation Approach (1996), Kluwer Academic Publisher: Kluwer Academic Publisher Dordrecht
[11] Weng, J.; Ahuja, N.; Huang, T. S., Motion and structure from point correspondences with error estimationPlanar surfaces, IEEE Trans. Signal Process., 39, 12, 2691-2717 (1991)
[12] Kamgar-Parsi, B.; Kamgar-Parsi, B., Matching sets of 3D line segments with application to polygonal arc matching, IEEE Trans. Pattern Anal. Mach. Intell., 19, 1090-1099 (1997)
[13] Kamgar-Pasi, B.; Magalit, A.; Rosenfeld, A., Matching general polygonal arcs, CVGIP: Image Understanding, 53, 227-234 (1991) · Zbl 0774.68097
[14] Persoon, E.; Fu, K. S., Shape discrimination using Fourier descriptors, IEEE Trans. Systems Man Cybernet., 7, 170-179 (1977)
[15] Cohen, F. S.; Huang, Z.; Yang, Z., Invariant matching and identification of curves using B-spline curve representation, IEEE Trans. Image Process., 4, 1-10 (1995)
[16] Cohen, F. S.; Wang, J., Modeling image curves using invariant 3D object curve models—a path to 3D recognition and shape estimation from image contours, IEEE Trans. Pattern Anal. Mach. Intell., 16, 1-23 (1994)
[17] Paulik, M. J.; Das, M.; Loh, N. K., Nonstationary autoregressive modeling of object contours, IEEE Trans. Signal Process., 40, 660-675 (1992)
[18] Flusser, J.; Suk, T., Pattern recognition by affine moment invariants, Pattern Recognition, 26, 167-174 (1993)
[19] Besl, P. J.; Jain, R. C., 3D object recognition, Comput. Surv., 17, 1, 75-145 (1985)
[20] A.L.N. Fred, J.S. Marques, P.M. Jorge, Hidden Markov models vs syntactic modeling in object recognition, Proceedings of International Conference on Image Processing (ICIP ’97), 1997, pp. 893-896.; A.L.N. Fred, J.S. Marques, P.M. Jorge, Hidden Markov models vs syntactic modeling in object recognition, Proceedings of International Conference on Image Processing (ICIP ’97), 1997, pp. 893-896.
[21] Tueng, Q. M.; Boles, W. W., Wavelet-based affine invariant representationa tool for recognizing planar objects in 3D space, IEEE Trans. Pattern Anal. Mach. Intell., 19, 846-857 (1997)
[22] de Boor, C., A practical guide to splines, Applied Mathematical Sciences, vol. 27 (1978), Springer: Springer Berlin · Zbl 0406.41003
[23] Arbter, K.; Snyder, W. E.; Burkhardr, H.; Hirzinger, G., Application of affine-invariant Fourier descriptors to recognition of 3D objects, IEEE Trans. Pattern Anal. Mach. Intell., 12, 452-459 (1990)
[24] Cyganski, D.; Vaz, R. F., A linear signal decomposition approach to affine invariant contour identification, Proc. SPIE: Intell. Robots Comput. Vision X, 1607, 98-109 (1991)
[25] Rogers, D. F.; Adames, J. A., Mathematical Elements for Computer Graphics (1990), McGraw-Hill Publishing Company: McGraw-Hill Publishing Company New York
[26] Cohen, F. S.; Wang, J., Modeling image curve using invariant 3-D object curve models—a path to 3-D recognition and shape estimation from image contours, IEEE Trans. Pattern Anal. Mach. Intell., 16, 1-12 (1994)
[27] Gu, Y. H., Adaptive multiresolution Hermite-Binomial filters for image edge and texture analysis, Proc. SPIE, 2308, 748-759 (1994)
[28] Liang, K. H.; Tjahjadi, T.; Yang, Y. H., Bounded diffusion for multiscale edge detection using regularized cubic B-spline fitting, IEEE Trans. Systems Man Cybernet., 29, 2, 291-297 (1999)
[29] Chen, B. D.; Siy, P., Forward/backward contour tracing with feedback, IEEE Trans. Pattern Anal. Mach. Intell., 9, 438-446 (1987)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.