PT Unknown
AU Bogdan Raducanu
   Fadi Dornaika
TI Out-of-Sample Embedding by Sparse Representation
BT Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop
PY 2012
BP 336
EP 344
VL 7626
DI 10.1007/978-3-642-34166-3_37
AB A critical aspect of non-linear dimensionality reduction techniques is represented by the construction of the adjacency graph. The difficulty resides in finding the optimal parameters, a process which, in general, is heuristically driven. Recently, sparse representation has been proposed as a non-parametric solution to overcome this problem. In this paper, we demonstrate that this approach not only serves for the graph construction, but also represents an efficient and accurate alternative for out-of-sample embedding. Considering for a case study the Laplacian Eigenmaps, we applied our method to the face recognition problem. Experimental results conducted on some challenging datasets confirmed the robustness of our approach and its superiority when compared to existing techniques.
ER