P. Penev and L.Sirovich. The global dimensionality of face space. In Proc. of IEEE Internation Conf. on Face and Gesture Recognition, pages 264--270, Grenoble, France, 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
The Application of Time-Frequency Methods to HUMS - Pryor, Mosher, G. (Correct)
....defining the model will be derived from data in the training set. By deriving the basis vectors for the model from the data rather than a standard expansion such as Fourier Series, data will fit better with fewer terms. This kind of modeling has been used to compress data for a variety of problems [27, 28, 29, 30, 31, 32, 33]. Several methods, Principal Component Analysis, Blind Signal Separation, Karhunen Love Transform and Singular Value Decomposition accomplish this modeling with the same mathematics. The modeling is described here within the framework of the Singular Value Decomposition. For modeling, the ....
....criteria are available. The number of modes can be chosen to account for a fixed amount of rms or variance in the training set [34] This method requires selecting a cutoff criteria. The number of modes can be chosen by examining the basis vectors and choosing only those that look like a signal [33]. This method is labor intensive and requires selecting a cutoff criteria. Another way is that the number of modes can be selected by statistical hypothesis testing of the multiplicity of a noise eigenvalue in the singular values to distinguish between noise and signal [35, 36, 37] The authors ....
Penev, Penio S. and Sirovich, Lawrence, "The Global Dimensionality of Face Space," Proceedings of Forth IEEE International Conference on Automatic Face and Gesture Recognition, March 2000.
Neural Coding and Decoding: Communication Channels and.. - Dimitrov, Miller (2001) (2 citations) (Correct)
....they are distinguishable, there will be an experiment that can resolve the issue. Even if we insist on considering continuous stimuli and responses, there are some arguments which again point to the benefit of discrete coding schemes. In the case of object and feature recognition, it was noted [24] that the continuity of stimuli is usually due to symmetries in the signal, which do not contribute to (and even interfere with) the recognition of features. The solution suggested in [24] is to pre process the stimulus to remove as much of the continuous symmetries as possible and then to ....
....point to the benefit of discrete coding schemes. In the case of object and feature recognition, it was noted [24] that the continuity of stimuli is usually due to symmetries in the signal, which do not contribute to (and even interfere with) the recognition of features. The solution suggested in [24] is to pre process the stimulus to remove as much of the continuous symmetries as possible and then to continue with the recognition algorithm. Another argument comes from recent work in rate distortion theory. It was shown [27] that the optimal reproduction space of a continuous source is ....
P. S. Penev and L. Sirovich. The global dimensionality of face space. In Proc. 4th Int'l Conf. Automatic Face and Gesture Recognition, pages 264--270, Grenoble, France, March 2000. IEEE CS Press.
Recognizing Imprecisely Localized, Partially Occluded and.. - Martinez (2002) (2 citations) (Correct)
....per class, there is no hope for the training data to underlie the true distribution of each subject. To successfully tackle the above defined problem, it is common to warp all faces to a standard shape (otherwise the PCA algorithm will also represent non desirable shape features of the face [49]) The procedure described in the previous section is such a mechanism. Note, however, that the proposed warping algorithm of Section 2.2 does not deform the important facial features. The shape of the eyes, mouth, nose, etc. is not affected. This is important because these facial features may ....
P.S. Penev and L. Sirovich, "The Global Dimensionality of Face Space," In Proc. IEEE Face and Gesture Recognition, pp. 264-270, 2000.
Redundancy and Dimensionality Reduction in Sparse-Distributed.. - Penev (2001) (3 citations) Self-citation (Penev) (Correct)
....of the retinal code is the same as that of the input. This situation is not typical. When KLT representations are derived for ensembles of natural objects, such as human faces (Sirovich and Kirby, 1987) the factorial codes in the resulting families are naturally low dimensional (Penev, 1998; Penev and Sirovich, 2000). Moreover, when a retinotopic organization is imposed, in a procedure called Local Feature Analysis (LFA) the resulting feed forward receptive fields are a dense set of detectors for the local features from which the objects are built (Penev and Atick, 1996) LFA has also been used to derive ....
.... r r (x)g, and are given by OE rec N = N X r=1 a r oe r r and OE err N = OE Gamma OE rec N : 3) 1 For the illustrations in this study, 2 T = T = 11254 frontal pose facial images were registered and normalized to a grid with V = 64 Theta 60 = 3840 pixels as previously described (Penev and Sirovich, 2000). 2 This is certainly true for in sample objects, since fa t r g are orthonormal (1) For out of sample objects, there is always the issue whether the size of the training sample, T , is sufficient to ensure proper generalization. The current ensemble has been found to generalize well in the ....
[Article contains additional citation context not shown here]
Penev, P. S. and L. Sirovich (2000). The global dimensionality of face space. In Proc. 4th Int'l Conf. Automatic Face and Gesture Recognition, Grenoble, France, pp. 264--270. IEEE CS.
Face Recognition in Subspaces - Shakhnarovich, Moghaddam (2004) (Correct)
No context found.
P. Penev and L.Sirovich. The global dimensionality of face space. In Proc. of IEEE Internation Conf. on Face and Gesture Recognition, pages 264--270, Grenoble, France, 2000.
Compensating for Ensemble-Specific Effects When Building.. - Costen, Cootes, Taylor (2000) (Correct)
No context found.
P. S. Penev and L. Sirovich. The Global Dimensionality of Face Space. 4th Face and Gesture, pages 264--270, 2000.
Face Recognition in Subspaces - Shakhnarovich, Moghaddam (2004) (Correct)
No context found.
P. Penev and L.Sirovich. The global dimensionality of face space. In Proc. of IEEE Internation Conf. on Face and Gesture Recognition, pages 264--270, Grenoble, France, 2000.
Face Class Modeling in Eigenfaces Space - Vlad Popovici And (2003) (Correct)
No context found.
Penev, P.S., Sirovich, L.: The global dimensionality of face space. In: Proceedings of the 4th Intl. Conference on Automatic Face and Gesture Recognition, IEEE CS (2000) 264--270
Face Detection Using an SVM Trained in Eigenfaces Space - Popovici, Thiran (2003) (Correct)
No context found.
Penev, P.S., Sirovich, L.: The global dimensionality of face space. In: Proceedings of the 4th Intl. Conference on Automatic Face and Gesture Recognition, IEEE CS (2000) 264--270
Data Mining in Forensic Image Databases - Geradts, Bijhold (Correct)
No context found.
P. Penev; L. Sirovich, The Global Dimensionality of Face Space", Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC