Title :
Recognition of 3D Objects Based on Implicit Polynomials
Author :
Ben-Yaacov, Hilla ; Malah, David ; Barzohar, Meir
Author_Institution :
Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel
fDate :
5/1/2010 12:00:00 AM
Abstract :
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.
Keywords :
object recognition; polynomials; pose estimation; 3D object recognition method; 3D rotation invariants; MPEG-7 SSD technique; closed-form expressions; implicit polynomial coefficient; pose estimation; 3D object fitting.; 3D object recognition; Implicit polynomials; rotation-invariant; tensor contraction; Algorithms; Artificial Intelligence; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2009.197
