Search For:

Displaying 1-25 out of 25 total
Appearance Characterization of Linear Lambertian Objects, Generalized Photometric Stereo, and Illumination-Invariant Face Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shaohua Kevin Zhou, Gaurav Aggarwal, Rama Chellappa, David W. Jacobs
Issue Date:February 2007
pp. 230-245
Traditional photometric stereo algorithms employ a Lambertian reflectance model with a varying albedo field and involve the appearance of only one object. In this paper, we generalize photometric stereo algorithms to handle all appearances of all objects i...
 
Localizing Parts of Faces Using a Consensus of Exemplars
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Peter N. Belhumeur,David W. Jacobs,David J. Kriegman,Neeraj Kumar
Issue Date:December 2013
pp. 2930-2940
We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images. By assuming tha...
 
Guest Editors' Introduction to the Special Section on Perceptual Organization in Computer Vision
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David W. Jacobs, Michael Lindenbaum
Issue Date:June 2003
pp. 641
No summary available.
 
Classification with Nonmetric Distances: Image Retrieval and Class Representation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David W. Jacobs, Daphna Weinshall, Yoram Gdalyahu
Issue Date:June 2000
pp. 583-600
<p><b>Abstract</b>—One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance, or that use robust image matching m...
 
In Search of Illumination Invariants
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs
Issue Date:June 2000
pp. 1254
We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We first show that for an object with Lambertian reflectance there are no discriminative functions that are invariant to illumination. T...
 
The Space Requirements of Indexing Under Perspective Projections
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David W. Jacobs
Issue Date:March 1996
pp. 330-333
<p><b>Abstract</b>—Object recognition systems can be made more efficient through the use of table lookup to match features. The cost of this <it>indexing</it> process depends on the space required to represent groups of model ...
 
Guest Editors' Introduction to the Special Section on Perceptual Organization in Computer Vision
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David W. Jacobs, Michael Lindenbaum
Issue Date:April 2003
pp. 385-386
No summary available.
 
Approximate earth mover's distance in linear time
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sameer Shirdhonkar, David W. Jacobs
Issue Date:June 2008
pp. 1-8
The earth mover’s distance (EMD) [16] is an important perceptually meaningful metric for comparing histograms, but it suffers from high (O(N<sup>3</sup> logN)) computational complexity. We present a novel linear time algorithm for approximating...
 
Non-Negative Lighting and Specular Object Recognition
Found in: Computer Vision, IEEE International Conference on
By Sameer Shirdhonkar, David W. Jacobs
Issue Date:October 2005
pp. 1323-1330
Recognition of specular objects is particularly difficult because their appearance is much more sensitive to lighting changes than that of Lambertian objects. We consider an approach in which we use a 3D model to deduce the lighting that best matches the m...
 
Deformation Invariant Image Matching
Found in: Computer Vision, IEEE International Conference on
By Haibin Ling, David W. Jacobs
Issue Date:October 2005
pp. 1466-1473
We propose a novel framework to build descriptors of local intensity that are invariant to general deformations. In this framework, an image is embedded as a 2D surface in 3D space, with intensity weighted relative to distance in x-y. We show that as this ...
 
On the Equivalence of Common Approaches to Lighting Insensitive Recognition
Found in: Computer Vision, IEEE International Conference on
By Margarita Osadchy, David W. Jacobs, Michael Lindenbaum
Issue Date:October 2005
pp. 1721-1726
Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighti...
 
Efficiently Determining Silhouette Consistency
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Li Yi, David W. Jacobs
Issue Date:June 2007
pp. 1-8
Volume intersection is a frequently used technique to solve the Shape-From-Silhouette problem, which constructs a 3D object estimate from a set of silhouettes taken with calibrated cameras. It is natural to develop an efficient algorithm to determine the c...
 
Surface Dependent Representations for Illumination Insensitive Image Comparison
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Margarita Osadchy, David W. Jacobs, Michael Lindenbaum
Issue Date:January 2007
pp. 98-111
We consider the problem of matching images to tell whether they come from the same scene viewed under different lighting conditions. We show that the surface characteristics determine the type of image comparison method that should be used. Previous work h...
 
Using the Inner-Distance for Classification of Articulated Shapes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Haibin Ling, David W. Jacobs
Issue Date:June 2005
pp. 719-726
We propose using the inner-distance between landmark points to build shape descriptors. The inner-distance is defined as the length of the shortest path between landmark points within the shape silhouette. We show that the inner-distance is articulation in...
 
Projective Alignment with Regions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ronen Basri, David W. Jacobs
Issue Date:May 2001
pp. 519-527
<p><b>Abstract</b>—We have recently proposed an approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. Regions introduce an attractive alternative to existing global...
 
Robust and Efficient Detection of Salient Convex Groups
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David W. Jacobs
Issue Date:January 1996
pp. 23-37
<p><b>Abstract</b>—This paper describes an algorithm that robustly locates <it>salient</it> convex collections of line segments in an image. The algorithm is guaranteed to find all convex sets of line segments in which the len...
 
Using Stereo Matching with General Epipolar Geometry for 2D Face Recognition across Pose
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Carlos D. Castillo, David W. Jacobs
Issue Date:December 2009
pp. 2298-2304
Face recognition across pose is a problem of fundamental importance in computer vision. We propose to address this problem by using stereo matching to judge the similarity of two, 2D images of faces seen from different poses. Stereo matching allows for arb...
 
A Study of Face Recognition as People Age
Found in: Computer Vision, IEEE International Conference on
By Haibin Ling, Stefano Soatto, Narayanan Ramanathan, David W. Jacobs
Issue Date:October 2007
pp. 1-8
In this paper we study face recognition across ages within a real passport photo verification task. First, we propose using the gradient orientation pyramid for this task. Discarding the gradient magnitude and utilizing hierarchical techniques, we found th...
 
Using Stereo Matching for 2-D Face Recognition Across Pose
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Carlos D. Castillo, David W. Jacobs
Issue Date:June 2007
pp. 1-8
We propose using stereo matching for 2-D face recognition across pose. We match one 2-D query image to one 2-D gallery image without performing 3-D reconstruction. Then the cost of this matching is used to evaluate the similarity of the two images. We show...
 
Shape Classification Using the Inner-Distance
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Haibin Ling, David W. Jacobs
Issue Date:February 2007
pp. 286-299
Part structure and articulation are of fundamental importance in computer and human vision. We propose using the inner-distance to build shape descriptors that are robust to articulation and capture part structure. The inner-distance is defined as the leng...
 
Lambertian Reflectance and Linear Subspaces
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ronen Basri, David W. Jacobs
Issue Date:February 2003
pp. 218-233
<p><b>Abstract</b>—We prove that the set of all Lambertian reflectance functions (the mapping from surface normals to intensities) obtained with arbitrary distant light sources lies close to a 9D linear subspace. This implies that, in gen...
 
3-D to 2-D Recognition with Regions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By David W. Jacobs, Ronen Basri
Issue Date:June 1997
pp. 547
This paper presents a novel approach to parts-based object recognition in the presence of occlusion. We focus on the problem of determining the pose of a 3-D object from a single 2-D image when convex parts of the object have been matched to corresponding ...
 
Local Parallel Computation of Stochastic Completion Fields
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lance R. Williams, David W. Jacobs
Issue Date:June 1996
pp. 161
We describe a local parallel method for computing the stochastic completion field introduced in an earlier paper\cite{williams}. The stochastic completion field represents the likelihood that a completion joining two contour fragments passes through any gi...
 
From Shading to Local Shape
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ying Xiong,Ayan Chakrabarti,Ronen Basri,Steven J. Gortler,David W. Jacobs,Todd Zickler
Issue Date:August 2014
pp. 1
We develop a framework for extracting a concise representation of the shape information available from diffuse shading in a small image patch. This produces a mid-level scene descriptor, comprised of local shape distributions that are inferred separately a...
 
Condensing Image Databases when Retrieval is Based on Non-Metric Distances
Found in: Computer Vision, IEEE International Conference on
By David W. Jacobs, Daphna Weinshall, Yoram Gdalyahu
Issue Date:January 1998
pp. 596
<p>One of the key problems in appearance-based-vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance, or that use robust image matching methods, often make use of si...
 
 1