Results 1  10
of
12
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.
Coding, Analysis, Interpretation, and Recognition of Facial Expressions
, 1997
"... We describe a computer vision system for observing facial motion by using an optimal estimation optical flow method coupled with geometric, physical and motionbased dynamic models describing the facial structure. Our method produces a reliable parametric representation of the face's independent mus ..."
Abstract

Cited by 262 (6 self)
 Add to MetaCart
We describe a computer vision system for observing facial motion by using an optimal estimation optical flow method coupled with geometric, physical and motionbased dynamic models describing the facial structure. Our method produces a reliable parametric representation of the face's independent muscle action groups, as well as an accurate estimate of facial motion. Previous efforts at analysis of facial expression have been based on the Facial Action Coding System (FACS), a representation developed in order to allow human psychologists to code expression from static pictures. To avoid use of this heuristic coding scheme, we have used our computer vision system to probabilistically characterize facial motion and muscle activation in an experimental population, thus deriving a new, more accurate representation of human facial expressions that we call FACS+. Finally, we show how this method can be used for coding, analysis, interpretation, and recognition of facial expressions.
Cooperative Robust Estimation Using Layers of Support
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1991
"... We present an approach to the problem of representing images that contain multiple objects or surfaces. Rather than use an edgebased approach to represent the segmentation of a scene, we propose a multilayer estimation framework which uses support maps to represent the segmentation of the image in ..."
Abstract

Cited by 86 (5 self)
 Add to MetaCart
We present an approach to the problem of representing images that contain multiple objects or surfaces. Rather than use an edgebased approach to represent the segmentation of a scene, we propose a multilayer estimation framework which uses support maps to represent the segmentation of the image into homogeneous chunks. This supportbased approach can represent objects that are split into disjoint regions, or have surfaces that are transparently interleaved. Our framework is based on an extension of robust estimation methods which provide a theoretical basis for supportbased estimation. The Minimum Description Length principle is used to decide how many support maps to use in describing a particular image. We show results applying this framework to heterogeneous interpolation and segmentation tasks on range and motion imagery. 1 Introduction Realworld perceptual systems must deal with complicated and cluttered environments. To succeed in such environments, a system must be able to r...
A Vision System for Observing and Extracting Facial Action Parameters
 PROCEEDINGS OF COMPUTER VISION AND PATTERN RECOGNITION (CVPR 94
, 1994
"... We describe a computer vision system for observing the "action units" of a face using video sequences as input. The visual observation (sensing) is achieved by using an optimal estimation optical flow method coupled with a geometric and a physical (muscle) model describing the facial structure. This ..."
Abstract

Cited by 69 (12 self)
 Add to MetaCart
We describe a computer vision system for observing the "action units" of a face using video sequences as input. The visual observation (sensing) is achieved by using an optimal estimation optical flow method coupled with a geometric and a physical (muscle) model describing the facial structure. This modeling results in a timevarying spatial patterning of facial shape and a parametric representation of the independent muscle action groups, responsible for the observed facial motions. These muscle action patterns may then be used for analysis, interpretation, and synthesis. Thus, by interpreting facial motions within a physicsbased optimal estimation framework, a new control model of facial movement is developed. The newly extracted action units (which we name "FACS+") are both physics and geometrybased, and extend the wellknown FACS parameters for facial expressions by adding temporal information and nonlocal spatial patterning of facial motion.
Automatic Reconstruction of 3D CAD Models from Digital Scans
 International Journal of Computational Geometry and Applications
, 1999
"... We present an approach for the reconstruction and approximation of 3D CAD models from an unorganized collection of points. Applications include rapid reverse engineering of existing objects for use in a synthetic computer environment, including computer aided design and manufacturing. Our reconstruc ..."
Abstract

Cited by 34 (9 self)
 Add to MetaCart
We present an approach for the reconstruction and approximation of 3D CAD models from an unorganized collection of points. Applications include rapid reverse engineering of existing objects for use in a synthetic computer environment, including computer aided design and manufacturing. Our reconstruction approach is flexible enough to permit interpolation of both smooth surfaces and sharp features, while placing few restrictions on the geometry or topology of the object. Our algorithm is based on alphashapes to compute an initial triangle mesh approximating the object's surface. A mesh reduction technique is applied to the dense triangle mesh to build a simplified approximation, while retaining important topological and geometric characteristics of the model. The reduced mesh is interpolated with piecewise algebraic surface patches which approximate the original points. The process is fully automatic, and the reconstruction is guaranteed to be homeomorphic and error bounded with respec...
Active Recognition: Using Uncertainty to Reduce Ambiguity
 IN PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION
, 1996
"... Ambiguity in scene information, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an informationbased utility measure is used to derive from ..."
Abstract

Cited by 18 (2 self)
 Add to MetaCart
Ambiguity in scene information, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an informationbased utility measure is used to derive from a learned classification of shape models an efficient data collection strategy, specifically aimed at increasing classification confidence when recognizing uncertain shapes. Promising experimental results are reported.
Informative Views and Sequential Recognition
 PROC. ECCV'96
, 1995
"... In this paper we introduce a method for distinguishing between informative and uninformative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
In this paper we introduce a method for distinguishing between informative and uninformative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are represented by conditional probability density functions. Consequently, the method also permits the assessment of the beliefs associated with a set of assertions based on data acquired from a particular viewpoint. The importance of this result is that it provides a basis by which an external agent can assess the quality of the information from a particular viewpoint, and make informed decisions as to what action to take using the data at hand. To illustrate the theory we show how the characteristics of belief distributions can be exploited in a modelbased recognition problem, where the task is to identify an unknown model from a database of known objects on the basis of parameter estimates. This leads to a sequential recognition strategy in which evidence is accumulated over successive viewpoints (at the level of the belief distribution) until a definitive assertion can be made. Experimental results are presented showing how the resulting algorithms can be used to distinguish between informative and uninformative viewpoints, rank a sequence of images on the basis of their information (e.g. to generate a set of characteristic views), and sequentially identify an unknown object.
Recognizing Volumetric Objects in the Presence of Uncertainty
 IN PROCEEDINGS 12TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION
, 1994
"... This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of refere ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of reference models. Our procedure is automatic. Offline, it invokes an autonomous process to estimate reference model parameters and their statistics. Online, during measurement, it combines these with apriori contextdependent information, as well as the parameters and statistics estimated for an unknown object, into a single description. That description, a conditional probability density function, represents the likelihood of correspondence between the unknown and a particular reference model. The paper also describes the implementation of this procedure in a system for automatically generating and recognizing 3D partoriented models. Specifically we show that recognition performance is near ...
Parametric Shape Recognition Using A Probabilistic Inverse Theory
"... . This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of r ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
. This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of reference models. Our procedure is automatic. Offline, it invokes an autonomous process to estimate reference model parameters and their statistics. Online, during measurement, it combines these with apriori contextdependent information, as well as the parameters and statistics estimated for an unknown object, into a single description. That description, a conditional probability density function, represents the likelihood of correspondence between the unknown and a particular reference model. The paper also describes the implementation of this procedure in a system for automatically generating and recognizing 3D partoriented models. Specifically we show that recognition performance is near perfect for cases in which complete surface information is accessible to the algorithm, and that it falls off gracefully (minimal falsepositive response) when only partial information is available. This leads to the possibility of an active recognition strategy in which the belief measures associated with each classification can be used as feedback for the acquisition of further evidence as required. Key words and phrases. object recognition, CPDF (Conditional Probability Density Function), belief distribution, informative viewpoints. PARAMETRIC SHAPE RECOGNITION USING A PROBABILISTIC INVERSE THEORY Abstract. This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key ...
Informative Views and Active Recognition
, 1994
"... In this paper we introduce a method for distinguishing between informative and uninformative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
In this paper we introduce a method for distinguishing between informative and uninformative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are represented by conditional probability density functions. Consequently, the method also permits the assessment of the beliefs associated with a set of assertions based on data acquired from a particular viewpoint. The importance of this result is that it provides a basis by which an external agent can assess the quality of the information from a particular viewpoint, and make informed decisions as to what action to take using the data at hand. What is important about the method is that it provides a formal recipe for representing and combining all prior knowledge in order to obtain the required density functions (which we refer to as belief distributions). To illustrate the theory we show ...