Results 1  10
of
88,007
An iterative image registration technique with an application to stereo vision
 In IJCAI81
, 1981
"... Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton ..."
Abstract

Cited by 2872 (35 self)
 Add to MetaCart
. The registration problem The translational image registration problem can be characterized as follows: We are given functions F(x) and G(x) which give the respective pixel values at each location x in two images, where x is a vector. We wish to find the disparity vector h which minimizes some measure
The Plenoptic Function and the Elements of Early Vision
 Computational Models of Visual Processing
, 1991
"... experiment. Electrophysiologists have described neurons in striate cortex that are selectively sensitive to certain visual properties; for reviews, see Hubel (1988) and DeValois and DeValois (1988). Psychophysicists have inferred the existence of channels that are tuned for certain visual properties ..."
Abstract

Cited by 573 (4 self)
 Add to MetaCart
properties; for reviews, see Graham (1989), Olzak and Thomas (1986), Pokorny and Smith (1986), and Watson (1986). Researchers in perception have found aspects of visual stimuli that are processed preattentively (Beck, 1966; Bergen & Julesz, 1983; Julesz & Bergen, Motion Color Binocular disparity
Light Field Rendering
, 1996
"... A number of techniques have been proposed for flying through scenes by redisplaying previously rendered or digitized views. Techniques have also been proposed for interpolating between views by warping input images, using depth information or correspondences between multiple images. In this paper, w ..."
Abstract

Cited by 1354 (22 self)
 Add to MetaCart
A number of techniques have been proposed for flying through scenes by redisplaying previously rendered or digitized views. Techniques have also been proposed for interpolating between views by warping input images, using depth information or correspondences between multiple images. In this paper, we describe a simple and robust method for generating new views from arbitrary camera positions without depth information or feature matching, simply by combining and resampling the available images. The key to this technique lies in interpreting the input images as 2D slices of a 4D function  the light field. This function completely characterizes the flow of light through unobstructed space in a static scene with fixed illumination. We describe a
LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares
 ACM Trans. Math. Software
, 1982
"... An iterative method is given for solving Ax ~ffi b and minU Ax b 112, where the matrix A is large and sparse. The method is based on the bidiagonalization procedure of Golub and Kahan. It is analytically equivalent to the standard method of conjugate gradients, but possesses more favorable numerica ..."
Abstract

Cited by 649 (21 self)
 Add to MetaCart
An iterative method is given for solving Ax ~ffi b and minU Ax b 112, where the matrix A is large and sparse. The method is based on the bidiagonalization procedure of Golub and Kahan. It is analytically equivalent to the standard method of conjugate gradients, but possesses more favorable numerical properties. Reliable stopping criteria are derived, along with estimates of standard errors for x and the condition number of A. These are used in the FORTRAN implementation of the method, subroutine LSQR. Numerical tests are described comparing I~QR with several other conjugategradient algorithms, indicating that I~QR is the most reliable algorithm when A is illconditioned. Categories and Subject Descriptors: G.1.2 [Numerical Analysis]: ApprorJmationleast squares approximation; G.1.3 [Numerical Analysis]: Numerical Linear Algebralinear systems (direct and
View Interpolation for Image Synthesis
"... Imagespace simplifications have been used to accelerate the calculation of computer graphic images since the dawn of visual simulation. Texture mapping has been used to provide a means by which images may themselves be used as display primitives. The work reported by this paper endeavors to carry t ..."
Abstract

Cited by 605 (0 self)
 Add to MetaCart
Imagespace simplifications have been used to accelerate the calculation of computer graphic images since the dawn of visual simulation. Texture mapping has been used to provide a means by which images may themselves be used as display primitives. The work reported by this paper endeavors to carry this concept to its logical extreme by using interpolated images to portray threedimensional scenes. The specialeffects technique of morphing, which combines interpolation of texture maps and their shape, is applied to computing arbitrary intermediate frames from an array of prestored images. If the images are a structured set of views of a 3D object or scene, intermediate frames derived by morphing can be used to approximate intermediate 3D transformations of the object or scene. Using the view interpolation approach to synthesize 3D scenes has two main advantages. First, the 3D representation of the scene may be replaced with images. Second, the image synthesis time is independent of the scene complexity. The correspondence between images, required for the morphing method, can be predetermined automatically using the range data associated with the images. The method is further accelerated by a quadtree decomposition and a viewindependent visible priority. Our experiments have shown that the morphing can be performed at interactive rates on today’s highend personal computers. Potential applications of the method include virtual holograms, a walkthrough in a virtual environment, imagebased primitives and incremental rendering. The method also can be used to greatly accelerate the computation of motion blur and soft shadows cast by area light sources.
A solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge
 PSYCHOLOGICAL REVIEW
, 1997
"... How do people know as much as they do with as little information as they get? The problem takes many forms; learning vocabulary from text is an especially dramatic and convenient case for research. A new general theory of acquired similarity and knowledge representation, latent semantic analysis (LS ..."
Abstract

Cited by 1772 (10 self)
 Add to MetaCart
How do people know as much as they do with as little information as they get? The problem takes many forms; learning vocabulary from text is an especially dramatic and convenient case for research. A new general theory of acquired similarity and knowledge representation, latent semantic analysis (LSA), is presented and used to successfully simulate such learning and several other psycholinguistic phenomena. By inducing global knowledge indirectly from local cooccurrence data in a large body of representative text, LSA acquired knowledge about the full vocabulary of English at a comparable rate to schoolchildren. LSA uses no prior linguistic or perceptual similarity knowledge; it is based solely on a general mathematical learning method that achieves powerful inductive effects by extracting the right number of dimensions (e.g., 300) to represent objects and contexts. Relations to other theories, phenomena, and problems are sketched.
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 831 (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.
Quantile Regression
 JOURNAL OF ECONOMIC PERSPECTIVES—VOLUME 15, NUMBER 4—FALL 2001—PAGES 143–156
, 2001
"... We say that a student scores at the fifth quantile of a standardized exam if he performs better than the proportion � of the reference group of students and worse than the proportion (1–�). Thus, half of students perform better than the median student and half perform worse. Similarly, the quartiles ..."
Abstract

Cited by 937 (10 self)
 Add to MetaCart
We say that a student scores at the fifth quantile of a standardized exam if he performs better than the proportion � of the reference group of students and worse than the proportion (1–�). Thus, half of students perform better than the median student and half perform worse. Similarly, the quartiles divide the population into four segments with equal proportions of the reference population in each segment. The quintiles divide the population into five parts; the deciles into ten parts. The quantiles, or percentiles, or occasionally fractiles, refer to the general case. Quantile regression as introduced by Koenker and Bassett (1978) seeks to extend these ideas to the estimation of conditional quantile functions—models in which quantiles of the conditional distribution of the response variable are expressed as functions of observed covariates. In Figure 1, we illustrate one approach to this task based on Tukey’s boxplot (as in McGill, Tukey and Larsen, 1978). Annual compensation for the chief executive officer (CEO) is plotted as a function of firm’s market value of equity. A sample of 1,660 firms was split into ten groups of equal size according to their market capitalization. For each group of 166 firms, we compute the three quartiles of CEO compensation: salary, bonus and other compensation, including stock options (as valued by the BlackScholes formula at the time of the grant). For each group, the bowtielike box represents the middle half of the salary distribution lying between the first and third quartiles. The horizontal line near the middle of each box represents the median compensation for each group of CEOs, and the
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a ViewBased Representation
 International Journal of Computer Vision
, 1998
"... This paper describes an approach for tracking rigid and articulated objects using a viewbased representation. The approach builds on and extends work on eigenspace representations, robust estimation techniques, and parameterized optical flow estimation. First, we note that the leastsquares image r ..."
Abstract

Cited by 656 (16 self)
 Add to MetaCart
This paper describes an approach for tracking rigid and articulated objects using a viewbased representation. The approach builds on and extends work on eigenspace representations, robust estimation techniques, and parameterized optical flow estimation. First, we note that the leastsquares image reconstruction of standard eigenspace techniques has a number of problems and we reformulate the reconstruction problem as one of robust estimation. Second we define a "subspace constancy assumption" that allows us to exploit techniques for parameterized optical flow estimation to solve for both the view of an object and the affine transformation between the eigenspace and the image. To account for large affine transformations between the eigenspace and the image we define a multiscale eigenspace representation and a coarsetofine matching strategy. Finally, we use these techniques to track objects over long image sequences in which the objects simultaneously undergo both affine image motions and changes of view. In particular we use this "EigenTracking" technique to track and recognize the gestures of a moving hand.
Results 1  10
of
88,007