Results 1  10
of
249
Detecting faces in images: A survey
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2002
"... Images containing faces are essential to intelligent visionbased human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods assume that the faces in an image or an image se ..."
Abstract

Cited by 595 (4 self)
 Add to MetaCart
Images containing faces are essential to intelligent visionbased human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face regardless of its threedimensional position, orientation, and the lighting conditions. Such a problem is challenging because faces are nonrigid and have a high degree of variability in size, shape, color, and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics, and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.
Probabilistic Visual Learning for Object Representation
, 1996
"... We present an unsupervised technique for visual learning which is based on density estimation in highdimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a Mixtureof ..."
Abstract

Cited by 561 (14 self)
 Add to MetaCart
We present an unsupervised technique for visual learning which is based on density estimation in highdimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a MixtureofGaussians model (for multimodal distributions). These probability densities are then used to formulate a maximumlikelihood estimation framework for visual search and target detection for automatic object recognition and coding. Our learning technique is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and nonrigid objects such as hands.
Probabilistic Visual Learning for Object Detection
, 1995
"... We present an unsupervised technique for visual learning which is based on density estimation in highdimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for a unimodal distribution) and a multivari ..."
Abstract

Cited by 210 (15 self)
 Add to MetaCart
We present an unsupervised technique for visual learning which is based on density estimation in highdimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for a unimodal distribution) and a multivariate MixtureofGaussians model (for multimodal distributions). These probability densities are then used to formulate a maximumlikelihood estimation framework for visual search and target detection for automatic object recognition. This learning technique is tested in experiments with modeling and subsequent detection of human faces and nonrigid objects such as hands.
The stationary behavior of ideal TCP congestion avoidance
, 1996
"... This note derives the stationary behavior of idealized TCP congestion avoidance. More specifically, it derives the stationary distribution of the congestion window size if loss of packets are independentevents with equal probability. The mathematical derivation uses a fluid flow, continuous time, ap ..."
Abstract

Cited by 129 (2 self)
 Add to MetaCart
This note derives the stationary behavior of idealized TCP congestion avoidance. More specifically, it derives the stationary distribution of the congestion window size if loss of packets are independentevents with equal probability. The mathematical derivation uses a fluid flow, continuous time, approximation to the discrete time process #W n #, where W n is the congestion window after the nth packet. We derive explicit results for the stationary distribution and all its moments. Congestion avoidance is the algorithm used by TCP to set its window size (and indirectly its data rate) under moderate to light segment (packet) losses. The congestion avoidance mechanism we model is idealized in the sense that loss of multiple packets does not lead to timeout phenomena. Such idealized behavior can be implemented using Selective Acknowledgements (SACKs). As such, our model predicts behavior of TCP with SACKs. It also is an approximate model in other situations. Among the results are that if eve...
Systems with finite communication bandwidth constraints—I: State estimation problems
 Stanford University, Stanford, CA
, 1997
"... Abstract—In this paper a new class of feedback control problems is introduced. Unlike classical models, the systems considered here have communication channel constraints. As a result, the issue of coding and communication protocol becomes an integral part of the analysis. Since these systems cannot ..."
Abstract

Cited by 114 (1 self)
 Add to MetaCart
Abstract—In this paper a new class of feedback control problems is introduced. Unlike classical models, the systems considered here have communication channel constraints. As a result, the issue of coding and communication protocol becomes an integral part of the analysis. Since these systems cannot be asymptotically stabilized if the underlying dynamics are unstable, a weaker stability concept called containability is introduced. A key result connects containability with an inequality equation involving the communication data rate and the rate of change of the state. Index Terms — Asymptotic stability, containability, feedback control, Kraft inequality.
Blind Separation of Mixture of Independent Sources Through a Maximum Likelihood Approach
 In Proc. EUSIPCO
, 1997
"... In this paper we propose two methods for separating mixtures of independent sources without any precise knowledge of their probability distribution. They are obtained by considering a maximum likelihood solution corresponding to some given distributions of the sources and relaxing this assumption af ..."
Abstract

Cited by 101 (8 self)
 Add to MetaCart
In this paper we propose two methods for separating mixtures of independent sources without any precise knowledge of their probability distribution. They are obtained by considering a maximum likelihood solution corresponding to some given distributions of the sources and relaxing this assumption afterward. The first method is specially adapted to temporally independent non Gaussian sources and is based on the use of nonlinear separating functions. The second method is specially adapted to correlated sources with distinct spectra and is based on the use of linear separating filters. A theoretical analysis of the performance of the methods has been made. A simple procedure for choosing optimally the separating functions from a given linear space of functions is proposed. Further, in the second method, a simple implementation based on the simultaneous diagonalization of two symmetric matrices is provided. Finally, some numerical and simulation results are given illustrating the performan...
Statistical Approach to Shape from Shading: Reconstruction of 3D Face Surfaces from Single 2D Images
 Neural Computation
, 1997
"... The human visual system is proficient in perceiving threedimensional shape from the shading patterns in a twodimensional image. How it does this is not well understood and continues to be a question of fundamental and practical interest. In this paper we present a new quantitative approach to shap ..."
Abstract

Cited by 95 (0 self)
 Add to MetaCart
The human visual system is proficient in perceiving threedimensional shape from the shading patterns in a twodimensional image. How it does this is not well understood and continues to be a question of fundamental and practical interest. In this paper we present a new quantitative approach to shapefromshading that may provide some answers. We suggest that the brain, through evolution or prior experience, has discovered that objects can be classified into lowerdimensional objectclasses as to their shape. Extraction of shape from shading is then equivalent to the much simpler problem of parameter estimation in a low dimensional space. We carry out this proposal for an important class of 3D objects; human heads. From an ensemble of several hundred laserscanned 3D heads, we use principal component analysis to derive a lowdimensional parameterization of head shape space. An algorithm for solving shapefromshading using this representation is presented. It works well even on real im...
Unified Notation for Data Assimilation: Operational, Sequential and Variational
, 1997
"... The need for unified notation in atmospheric and oceanic data assimilation arises from the field's rapid theoretical expansion and the desire to translate it into practical applications. Selfconsistent notation is proposed that bridges sequential and variational methods, on the one hand, and operat ..."
Abstract

Cited by 91 (8 self)
 Add to MetaCart
The need for unified notation in atmospheric and oceanic data assimilation arises from the field's rapid theoretical expansion and the desire to translate it into practical applications. Selfconsistent notation is proposed that bridges sequential and variational methods, on the one hand, and operational usage, on the other. Over various other mottoes for this risky endeavor, the authors selected: "When I use a word," Humpty Dumpty said, in rather a scornful voice tone, "it means just what I choose it to mean  neither more nor less." Lewis Carroll, 1871. 1 J. Met. Soc. Japan, Special Issue on "Data Assimilation in Meteorology and Oceanography: Theory and Practice." Vol. 75, No. 1B, pp. 181189, 1997. 2 Corresponding author. 3 Current affiliation: CNES, 2, place Maurice Quentin, 75039 Paris Cedex 01, France. 1 J. Met. Soc. Japan, (1997), K. Ide, P. Courtier, M. Ghil and A.C. Lorenc 2 1. Introduction and motivation Modelbased assimilation of observations, or data assimilati...
Optimal Taxation without StateContingent Debt
, 1996
"... To recover a version of Barro's (1979) `random walk' tax smoothing outcome, we modify Lucas and Stokey's (1983) economy to permit only riskfree debt. This imparts near unit root like behavior to government debt, independently of the government expenditure process, a realistic outcome in the spirit ..."
Abstract

Cited by 86 (11 self)
 Add to MetaCart
To recover a version of Barro's (1979) `random walk' tax smoothing outcome, we modify Lucas and Stokey's (1983) economy to permit only riskfree debt. This imparts near unit root like behavior to government debt, independently of the government expenditure process, a realistic outcome in the spirit of Barro's. We show how the riskfreedebtonly economy confronts the Ramsey planner with additional constraints on equilibrium allocations that take the form of a sequence of measurability conditions. We solve the Ramsey problem by formulating it in terms of a Lagrangian, and applying a Parameterized Expectations Algorithm to the associated firstorder conditions. The firstorder conditions and numerical impulse response functions partially affirm Barro's random walk outcome. Though the behaviors of tax rates, government surpluses, and government debts differ, allocations are very close for computed Ramsey policies across incomplete and complete markets economies.
Adversarial Queuing Theory
, 2001
"... We consider packet routing when packets are injected continuously into a network. We develop an adversarial theory of queuing aimed at addressing some of the restrictions inherent in probabilistic analysis and queuing theory based on timeinvariant stochastic generation. We examine the stability of ..."
Abstract

Cited by 75 (0 self)
 Add to MetaCart
We consider packet routing when packets are injected continuously into a network. We develop an adversarial theory of queuing aimed at addressing some of the restrictions inherent in probabilistic analysis and queuing theory based on timeinvariant stochastic generation. We examine the stability of queuing networks and policies when the arrival process is adversarial, and provide some preliminary results in this direction. Our approach sheds light on various queuing policies in simple networks, and paves the way for a systematic study of queuing with few or no probabilistic assumptions.