26 February 2008 A modular non-negative matrix factorization for parts-based object recognition using subspace representation
Author Affiliations +
Non-negative matrix factorization of an input data matrix into a matrix of basis vectors and a matrix of encoding coefficients is a subspace representation method that has attracted attention of researches in pattern recognition in the recent period. We have explored crucial aspects of NMF on massive recognition experiments with the ORL database of faces which include intuitively clear parts constituting the whole. Using a principal changing of the learning stage structure and by formulating NMF problems for each of a priori given parts separately, we developed a novel modular NMF algorithm. Although this algorithm provides uniquely separated basis vectors which code individual face parts in accordance with the parts-based principle of the NMF methodology applied to object recognition problems, any significant improvement of recognition rates for occluded parts, predicted in several papers, was not reached. We claim that using the parts-based concept in NMF as a basis for solving recognition problems with occluded objects has not been justified.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ivan Bajla, Ivan Bajla, Daniel Soukup, Daniel Soukup, "A modular non-negative matrix factorization for parts-based object recognition using subspace representation", Proc. SPIE 6813, Image Processing: Machine Vision Applications, 68130C (26 February 2008); doi: 10.1117/12.760365; https://doi.org/10.1117/12.760365


Detection and tracking of facial features
Proceedings of SPIE (April 20 1995)
Face location and recognition
Proceedings of SPIE (April 21 1996)
Face recognition based on eigenfeatures
Proceedings of SPIE (September 20 2001)
Directional symmetry transform for human face location
Proceedings of SPIE (September 24 1998)

Back to Top