Issue No. 05 - May (2010 vol. 32)
Hilla Ben-Yaacov , Technion-Israel Institute of Technology, Haifa
David Malah , Technion-Israel Institute of Technology, Haifa
Meir Barzohar , Technion-Israel Institute of Technology, Haifa
Closed-form expressions for a new set of 3D rotation invariants that are linear, quadratic, and angular combinations of implicit polynomial (IP) coefficients are developed. Based on these invariants, we propose a 3D object recognition method that outperforms recognition based on IP fitting after pose estimation, and the MPEG-7 SSD technique.
Implicit polynomials, 3D object recognition, tensor contraction, rotation-invariant, 3D object fitting.
M. Barzohar, H. Ben-Yaacov and D. Malah, "Recognition of 3D Objects Based on Implicit Polynomials," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 32, no. , pp. 954-960, 2009.