Results 1  10
of
115
Face Recognition: A Literature Survey
, 2000
"... ... This paper provides an uptodate critical survey of still and videobased face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an uptodate review of the existing literature, and the second is to offer some insights into ..."
Abstract

Cited by 859 (21 self)
 Add to MetaCart
... This paper provides an uptodate critical survey of still and videobased face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an uptodate review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition,
A theory of cortical responses
, 2005
"... This article concerns the nature of evoked brain responses and the principles underlying their generation. We start with the premise that the sensory brain has evolved to represent or infer the causes of changes in its sensory inputs. The problem of inference is well formulated in statistical terms. ..."
Abstract

Cited by 100 (21 self)
 Add to MetaCart
This article concerns the nature of evoked brain responses and the principles underlying their generation. We start with the premise that the sensory brain has evolved to represent or infer the causes of changes in its sensory inputs. The problem of inference is well formulated in statistical terms. The statistical fundaments of inference may therefore afford important constraints on neuronal implementation. By formulating the original ideas of Helmholtz on perception, in terms of modernday statistical theories, one arrives at a model of perceptual inference and learning that can explain a remarkable range of neurobiological facts. It turns out that the problems of inferring the causes of sensory input (perceptual inference) and learning the relationship between input and cause (perceptual learning) can be resolved using exactly the same principle. Specifically, both inference and learning rest on minimizing the brain’s free energy, as defined in statistical physics. Furthermore, inference and learning can proceed in a biologically plausible fashion. Cortical responses can be seen as the brain’s attempt to minimize the free energy induced by a stimulus and thereby encode the most likely cause of that stimulus. Similarly, learning emerges from changes in synaptic efficacy that minimize the free energy, averaged over all stimuli encountered. The underlying scheme rests on empirical Bayes and hierarchical models
Graphical models and automatic speech recognition
 Mathematical Foundations of Speech and Language Processing
, 2003
"... Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recog ..."
Abstract

Cited by 67 (13 self)
 Add to MetaCart
Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recognition techniques commonly used as part of a speech recognition system can be described by a graph – this includes Gaussian distributions, mixture models, decision trees, factor analysis, principle component analysis, linear discriminant analysis, and hidden Markov models. Moreover, this paper shows that many advanced models for speech recognition and language processing can also be simply described by a graph, including many at the acoustic, pronunciation, and languagemodeling levels. A number of speech recognition techniques born directly out of the graphicalmodels paradigm are also surveyed. Additionally, this paper includes a novel graphical analysis regarding why derivative (or delta) features improve hidden Markov modelbased speech recognition by improving structural discriminability. It also includes an example where a graph can be used to represent language model smoothing constraints. As will be seen, the space of models describable by a graph is quite large. A thorough exploration of this space should yield techniques that ultimately will supersede the hidden Markov model.
Blind Separation of Delayed and Convolved Sources
, 1997
"... We address the difficult problem of separating multiple speakers with multiple microphones in a real room. We combine the work of Torkkola and Amari, Cichocki and Yang, to give Natural Gradient information maximisation rules for recurrent (IIR) networks, blindly adjusting delays, separating and deco ..."
Abstract

Cited by 63 (1 self)
 Add to MetaCart
We address the difficult problem of separating multiple speakers with multiple microphones in a real room. We combine the work of Torkkola and Amari, Cichocki and Yang, to give Natural Gradient information maximisation rules for recurrent (IIR) networks, blindly adjusting delays, separating and deconvolving mixed signals. While they work well on simulated data, these rules fail in real rooms which usually involve nonminimum phase transfer functions, notinvertible using stable IIR filters. An approach that sidesteps this problem is to perform infomax on a feedforward architecture in the frequency domain (Lambert 1996). We demonstrate realroom separation of two natural signals using this approach. 1 The problem. In the linear blind signal processing problem ([3, 2] and references therein), N signals, s(t) = [s 1 (t) : : : s N (t)] T , are transmitted through a medium so that an array of N sensors picks up a set of signals x(t) = [x 1 (t) : : : xN (t)] T , each of which has bee...
Energybased models for sparse overcomplete representations
 Journal of Machine Learning Research
, 2003
"... We present a new way of extending independent components analysis (ICA) to overcomplete representations. In contrast to the causal generative extensions of ICA which maintain marginal independence of sources, we define features as deterministic (linear) functions of the inputs. This assumption resul ..."
Abstract

Cited by 51 (14 self)
 Add to MetaCart
We present a new way of extending independent components analysis (ICA) to overcomplete representations. In contrast to the causal generative extensions of ICA which maintain marginal independence of sources, we define features as deterministic (linear) functions of the inputs. This assumption results in marginal dependencies among the features, but conditional independence of the features given the inputs. By assigning energies to the features a probability distribution over the input states is defined through the Boltzmann distribution. Free parameters of this model are trained using the contrastive divergence objective (Hinton, 2002). When the number of features is equal to the number of input dimensions this energybased model reduces to noiseless ICA and we show experimentally that the proposed learning algorithm is able to perform blind source separation on speech data. In additional experiments we train overcomplete energybased models to extract features from various standard datasets containing speech, natural images, handwritten digits and faces.
Ensemble learning for independent component analysis
 in Advances in Independent Component Analysis
, 2000
"... i Abstract This thesis is concerned with the problem of Blind Source Separation. Specifically we considerthe Independent Component Analysis (ICA) model in which a set of observations are modelled by xt = Ast: (1) where A is an unknown mixing matrix and st is a vector of hidden source components atti ..."
Abstract

Cited by 49 (2 self)
 Add to MetaCart
i Abstract This thesis is concerned with the problem of Blind Source Separation. Specifically we considerthe Independent Component Analysis (ICA) model in which a set of observations are modelled by xt = Ast: (1) where A is an unknown mixing matrix and st is a vector of hidden source components attime t. The ICA problem is to find the sources given only a set of observations. In chapter 1, the blind source separation problem is introduced. In chapter 2 the methodof Ensemble Learning is explained. Chapter 3 applies Ensemble Learning to the ICA model and chapter 4 assesses the use of Ensemble Learning for model selection.Chapters 57 apply the Ensemble Learning ICA algorithm to data sets from physics (a medical imaging data set consisting of images of a tooth), biology (data sets from cDNAmicroarrays) and astrophysics (Planck image separation and galaxy spectra separation).
Flexible Independent Component Analysis
, 2000
"... This paper addresses an independent component analysis (ICA) learning algorithm with flexible nonlinearity, so named as flexible ICA, that is able to separate instantaneous mixtures of suband superGaussian source signals. In the framework of natural Riemannian gradient, we employ the parameterized ..."
Abstract

Cited by 43 (13 self)
 Add to MetaCart
This paper addresses an independent component analysis (ICA) learning algorithm with flexible nonlinearity, so named as flexible ICA, that is able to separate instantaneous mixtures of suband superGaussian source signals. In the framework of natural Riemannian gradient, we employ the parameterized generalized Gaussian density model for hypothesized source distributions. The nonlinear function in the flexible ICA algorithm is controlled by the Gaussian exponent according to the estimated kurtosis of demixing filter output. Computer simulation results and performance comparison with existing methods are presented.
Ensemble Learning for Blind Image Separation and Deconvolution
, 2000
"... Introduction Previous work on Blind Source Deconvolution has focused mainly on the problem of deconvolving sound samples. It is assumed that the observed sound samples are temporally convolved versions of the true source samples. Blind Deconvolution algorithms have fallen into two types, those wher ..."
Abstract

Cited by 41 (0 self)
 Add to MetaCart
Introduction Previous work on Blind Source Deconvolution has focused mainly on the problem of deconvolving sound samples. It is assumed that the observed sound samples are temporally convolved versions of the true source samples. Blind Deconvolution algorithms have fallen into two types, those where the inverse of the convolution lter is learnt [1],[3] and those where the aim is to learn the lter itself [1]. When applying these ideas to the problem of deconvolving images two problems become apparent. Firstly in many real data sets (for instance the images generated by telescopes observing the sky or the power spectrum from a Nuclear Magnetic Resonance (NMR) spectrometer) the pixel values correspond to intensities. So the pixel values must be positive. The standard blind separation approaches of assuming that the sources are distributed as 1 cosh [3] or mixtures of Gaussians [2] lose this positivity of the source images. Deconvolution without a positivity con