VIEW-BASED 3 D OBJECT RECOGNITION WITH SUPPORT VECTOR MACHINES

Support Vector Machines have demonstrated excellent results in pattern recognition tasks and 3D object recognition. In this contribution, we confirm some of the results in 3D object recognition and compare it to other object recognition systems. We use different pixel-level representations to perform the experiments, while we extend the setting to the more challenging and practical case when only a limited number of views of the object are presented during training. We report high correct classification of unseen views, especially considering that no domain knowledge is including into the proposed system. Finally, we suggest an active learning algorithm to reduce further the required number of

[1]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[2]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Bernhard Schölkopf,et al.  Extracting Support Data for a Given Task , 1995, KDD.

[4]  Harris Drucker,et al.  Comparison of learning algorithms for handwritten digit recognition , 1995 .

[5]  Bernhard Schölkopf,et al.  Comparison of View-Based Object Recognition Algorithms Using Realistic 3D Models , 1996, ICANN.

[6]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[7]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[8]  Hiroshi Murase,et al.  Real-time 100 object recognition system , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[9]  Massimiliano Pontil,et al.  Properties of Support Vector Machines , 1998, Neural Computation.

[10]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Alexander J. Smola,et al.  Support Vector Machine Reference Manual , 1998 .