Abstract
A scheme for learning and recognizing 3D objects from their 2D views is presented. The scheme proceeds in two stages. In the first stage, we try to learn a model automatically from 2D training images of different objects which have similar shape of components and similar adjacency relation between the components. In the second stage, the generated model is used to recognize the learned object. We use partial planar curve matching method to implement our scheme. We tested the approach on recognizing objects from images of complex real scenes and got satisfactory results.
Preview
Unable to display preview. Download preview PDF.
References
Ullman, S.: High-level vision, The MIT Press, 1995
Sugiyama, T., Abe, K.: Image segmentation using both edge and region information. Proc. of IAPR Workshop on Machine Vision Application, MVA'94, Kawasaki, Japan, (1994) 127–130.
Wang, C., Abe, K.: Region correspondence by inexact attributed planar graph matching. Proc. 5th ICCV, (1995) 440-447.
Held, A., Abe, K.: On approximate convexity. Pattern recognition letters. Vol.15 No.6 (1994) 611–618
Pikaz, A., Dinstein, I.: Matching of partial occluded planar curves. Pattern Recognition. Vol. 28 No.2 (1995) 199–209
Abe, K., Morii, R., Nishida, K., Kadonage, T., Comparison of methods for detecting corner points from digital curves — a preliminary report. Proc. 2nd Int'1 Conf. on Document Analysis and Recognition. (1993) 854–857
Haralick, R., M., Shapiro, L., G.: Computer and robot vision. Chap. 18, Addison-Wesley Publishing, (1993)
Basri, R.: Recognition by prototype. Proc. Conf. on Computer Vision and Pattern Recognition. (1993) 161–167
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jia, J., Abe, K. (1997). Learning and recognizing 3D objects by using partial planar curve matching method. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_153
Download citation
DOI: https://doi.org/10.1007/3-540-63930-6_153
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63930-5
Online ISBN: 978-3-540-69669-8
eBook Packages: Springer Book Archive