Weinshall, Daphna
Overview
Works:  28 works in 50 publications in 1 language and 382 library holdings 

Genres:  Conference proceedings 
Roles:  Author, Editor, Thesis advisor 
Classifications:  Q325.5, 006.31 
Publication Timeline
.
Most widely held works by
Daphna Weinshall
Detection and identification of rare audiovisual cues by
Daphna Weinshall(
)
7 editions published between 2011 and 2013 in English and held by 328 WorldCat member libraries worldwide
Machine learning builds models of the world using training data from the application domain and prior knowledge about the problem. The models are later applied to future data in order to estimate the current state of the world. An implied assumption is that the future is stochastically similar to the past. The approach fails when the system encounters situations that are not anticipated from the past experience. In contrast, successful natural organisms identify new unanticipated stimuli and situations and frequently generate appropriate responses. The observation described above lead to the initiation of the DIRAC EC project in 2006. In 2010 a workshop was held, aimed to bring together researchers and students from different disciplines in order to present and discuss new approaches for identifying and reacting to unexpected events in informationrich environments. This book includes a summary of the achievements of the DIRAC project in chapter 1, and a collection of the papers presented in this workshop in the remaining parts
7 editions published between 2011 and 2013 in English and held by 328 WorldCat member libraries worldwide
Machine learning builds models of the world using training data from the application domain and prior knowledge about the problem. The models are later applied to future data in order to estimate the current state of the world. An implied assumption is that the future is stochastically similar to the past. The approach fails when the system encounters situations that are not anticipated from the past experience. In contrast, successful natural organisms identify new unanticipated stimuli and situations and frequently generate appropriate responses. The observation described above lead to the initiation of the DIRAC EC project in 2006. In 2010 a workshop was held, aimed to bring together researchers and students from different disciplines in order to present and discuss new approaches for identifying and reacting to unexpected events in informationrich environments. This book includes a summary of the achievements of the DIRAC project in chapter 1, and a collection of the papers presented in this workshop in the remaining parts
Qualitative depth and shape from stereo, in agreement with psychophysical evidence by
Daphna Weinshall(
Book
)
1 edition published in 1987 in English and held by 5 WorldCat member libraries worldwide
1 edition published in 1987 in English and held by 5 WorldCat member libraries worldwide
The matching of doubly ambiguous stereograms by
Daphna Weinshall(
Book
)
2 editions published in 1991 in English and held by 4 WorldCat member libraries worldwide
Algorithms that can be modified to perform consistently with human perception, and the constraints imposed on their parameters by human perception, are discussed."
2 editions published in 1991 in English and held by 4 WorldCat member libraries worldwide
Algorithms that can be modified to perform consistently with human perception, and the constraints imposed on their parameters by human perception, are discussed."
Condensing image databases when retrieval is based on nonmetric distances by
Daphna Weinshall(
Book
)
3 editions published in 1997 in English and held by 4 WorldCat member libraries worldwide
Abstract: "One of the key problems in appearancebased 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 similarity judgments that are nonmetric; but when the triangle inequality is not obeyed, most existing pattern recognition techniques are not applicable. We note that exemplarbased (or nearestneighbor) methods can be applied naturally when using a wide class of nonmetric similarity functions. The key issue, however, is to find methods for choosing good representatives of a class that accurately characterize it. We show that existing condensing techniques for finding class representatives are illsuited to deal with nonmetric dataspaces. We then focus on developing techniques for solving this problem, emphasizing two points: First, we show that the distance between two images is not a good measure of how well one image can represent another in nonmetric spaces. Instead, we use the vector correlation between the distances from each image to other previously seen images. Second, we show that in nonmetric spaces, boundary points are less significant for capturing the structure of a class than they are in Euclidean spaces. We suggest that atypical points may be more important in describing classes. We demonstrate the importance of these ideas to learning that generalizes from experience by improving performance using both synthetic and real images."
3 editions published in 1997 in English and held by 4 WorldCat member libraries worldwide
Abstract: "One of the key problems in appearancebased 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 similarity judgments that are nonmetric; but when the triangle inequality is not obeyed, most existing pattern recognition techniques are not applicable. We note that exemplarbased (or nearestneighbor) methods can be applied naturally when using a wide class of nonmetric similarity functions. The key issue, however, is to find methods for choosing good representatives of a class that accurately characterize it. We show that existing condensing techniques for finding class representatives are illsuited to deal with nonmetric dataspaces. We then focus on developing techniques for solving this problem, emphasizing two points: First, we show that the distance between two images is not a good measure of how well one image can represent another in nonmetric spaces. Instead, we use the vector correlation between the distances from each image to other previously seen images. Second, we show that in nonmetric spaces, boundary points are less significant for capturing the structure of a class than they are in Euclidean spaces. We suggest that atypical points may be more important in describing classes. We demonstrate the importance of these ideas to learning that generalizes from experience by improving performance using both synthetic and real images."
The shape of shading by
Daphna Weinshall(
Book
)
3 editions published in 1990 in English and held by 4 WorldCat member libraries worldwide
This paper discusses the relationship between the shape of the shading, the surface whose depth at each point equals the brightness in the image, and the shape of the original surface. I suggest the shading as an initial local approximation to shape, and discuss the scope of this approximation and what it may be good for. In particular, qualitative surface features, such as the sign of the Gaussian curvature, can be computed in some cases directly from the shading. Finally, a method to compute the direction of the illuminant (assuming a single point light source) from shading on occluding contours is shown
3 editions published in 1990 in English and held by 4 WorldCat member libraries worldwide
This paper discusses the relationship between the shape of the shading, the surface whose depth at each point equals the brightness in the image, and the shape of the original surface. I suggest the shading as an initial local approximation to shape, and discuss the scope of this approximation and what it may be good for. In particular, qualitative surface features, such as the sign of the Gaussian curvature, can be computed in some cases directly from the shading. Finally, a method to compute the direction of the illuminant (assuming a single point light source) from shading on occluding contours is shown
Seeing ghost solutions in stereo vision by
Daphna Weinshall(
Book
)
1 edition published in 1988 in English and held by 3 WorldCat member libraries worldwide
A unique matching is a stated objective of most computational theories of stereo vision. This report describes situations where humans perceive a small number of surfaces carried by nonunique matching of random dot patterns, although a unique solution exists and is observed unambiguously in the perception of isolated features. We find both cases where nonunique matchings compete and suppress each other and cases where they are all perceived as transparent surfaces. The circumstances under which each behavior occurs are discussed and a possible explanation is sketched. It appears that matching reduces many false targets to a few, but may still yield multiple solutions in some cases through a (possibly different) process of surface interpolation
1 edition published in 1988 in English and held by 3 WorldCat member libraries worldwide
A unique matching is a stated objective of most computational theories of stereo vision. This report describes situations where humans perceive a small number of surfaces carried by nonunique matching of random dot patterns, although a unique solution exists and is observed unambiguously in the perception of isolated features. We find both cases where nonunique matchings compete and suppress each other and cases where they are all perceived as transparent surfaces. The circumstances under which each behavior occurs are discussed and a possible explanation is sketched. It appears that matching reduces many false targets to a few, but may still yield multiple solutions in some cases through a (possibly different) process of surface interpolation
The evolution of sexual reproduction a mathematical model by
Daphna Weinshall(
Book
)
3 editions published in 1986 in English and held by 3 WorldCat member libraries worldwide
3 editions published in 1986 in English and held by 3 WorldCat member libraries worldwide
Stimulus familiarity determines recognition strategy for novel 3D objects by
Shimon Edelman(
Book
)
2 editions published in 1989 in English and held by 3 WorldCat member libraries worldwide
2 editions published in 1989 in English and held by 3 WorldCat member libraries worldwide
Distance metric between 3D models and 2D images for recognition and classification by R Basri(
Book
)
3 editions published between 1992 and 1994 in English and held by 3 WorldCat member libraries worldwide
In this paper we introduce a different type of metrics: transformation metrics. These metrics penalize for the deformations applied to the object to produce the observed image. We present a transformation metric that optimally penalizes for 'affine deformations' under weakperspective. A closedform solution, together with the nearest view according to this metric, are derived. The metric is shown to be equivalent to the Euclidean image metric, in the sense that they bound each other from both above and below. For the Euclidean image metric we offer a suboptimal closedform solution and an iterative scheme to compute the exact solution."
3 editions published between 1992 and 1994 in English and held by 3 WorldCat member libraries worldwide
In this paper we introduce a different type of metrics: transformation metrics. These metrics penalize for the deformations applied to the object to produce the observed image. We present a transformation metric that optimally penalizes for 'affine deformations' under weakperspective. A closedform solution, together with the nearest view according to this metric, are derived. The metric is shown to be equivalent to the Euclidean image metric, in the sense that they bound each other from both above and below. For the Euclidean image metric we offer a suboptimal closedform solution and an iterative scheme to compute the exact solution."
Computational Vision: A Critical Review by
Shimon Edelman(
Book
)
2 editions published in 1989 in English and held by 2 WorldCat member libraries worldwide
The progress made in computational vision, as represented by Marr's approach is reviewed. Outlined briefly is computational theories developed for low, middle and high vision. Then more detail solutions proposed to three representative problems in vision are discussed, each dealing with a different level of visual processing. Finally, are discussed modifications to the currently established computational paradigm that appear to be directed by the recent developments in vision
2 editions published in 1989 in English and held by 2 WorldCat member libraries worldwide
The progress made in computational vision, as represented by Marr's approach is reviewed. Outlined briefly is computational theories developed for low, middle and high vision. Then more detail solutions proposed to three representative problems in vision are discussed, each dealing with a different level of visual processing. Finally, are discussed modifications to the currently established computational paradigm that appear to be directed by the recent developments in vision
Complexity of indexing : efficient and learnable large database indexing by Michael Werman(
Book
)
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Object recognition starts from a set of image measurements (including locations of points, lines, surfaces, color, and shading), which provides access into a database where representations of objects are stored. We describe a complexity theory of indexing, a meta analysis which identifies the best set of measurements (up to algebraic transformations) such that: (1) the representation of objects are linear subspaces and thus easy to learn; (2) direct indexing is efficient since the linear subspaces are of minimal rank. Index complexity is determined via a simple process, equivalent to computing the rank of a matrix. We readily rederive the index complexity of the few previously analyzed cases. We then compute the best index for new and more interesting cases: 6 points in one perspective image, 6 directions in one paraperspective image, and 2 perspective images of 7 points. With color we get the following result: 4 color sensors are sufficient for color constancy at a point, and the sensoroutput index is irreducible; the most efficient representation of a color is a plane in 3D space. For future applications with any vision problem where the relations between shape and image measurements can be written down, we give an automatic process to construct the most efficient database that can be directly obtained by learning from examples."
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Object recognition starts from a set of image measurements (including locations of points, lines, surfaces, color, and shading), which provides access into a database where representations of objects are stored. We describe a complexity theory of indexing, a meta analysis which identifies the best set of measurements (up to algebraic transformations) such that: (1) the representation of objects are linear subspaces and thus easy to learn; (2) direct indexing is efficient since the linear subspaces are of minimal rank. Index complexity is determined via a simple process, equivalent to computing the rank of a matrix. We readily rederive the index complexity of the few previously analyzed cases. We then compute the best index for new and more interesting cases: 6 points in one perspective image, 6 directions in one paraperspective image, and 2 perspective images of 7 points. With color we get the following result: 4 color sensors are sufficient for color constancy at a point, and the sensoroutput index is irreducible; the most efficient representation of a color is a plane in 3D space. For future applications with any vision problem where the relations between shape and image measurements can be written down, we give an automatic process to construct the most efficient database that can be directly obtained by learning from examples."
Shape descriptors : bilinear, trilinear, and quadrilinear relations for multipoint geometry by
Daphna Weinshall(
Book
)
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "The geometry of 1 point in N images under perspective projection has been thoroughly investigated, identifying bilinear, trilinear, and quadrilinear relations between the projections of 1 point in 2, 3 and 4 frames respectively. The dual problem  the geometry of N points in 1 image  has been studied mostly in the context of object recognition, often assuming weak perspective or affine projection. We provide here a complete description of this problem. We employ a formalism in which multiframe and multipoint geometries appear in symmetry: points and projections are interchangeable. We then derive bilinear equations for 6 points (dual to 4frame geometry), trilinear equations for 7 points (dual to 3frame geometry), and quadrilinear equations for 8 points (dual to the epipolar geometry). We show that the quadrilinear equations are dependent on the the [sic] bilinear and trilinear equations, and that adding more points will not generate any new equation. Applications to reconstruction and recognition: The new equations are used to design new algorithms for the reconstruction of shape from many frames, and for learning invariant relations for indexing into a database. We describe algorithms which require matching 6 (or more) corresponding points from at least 4 images, 7 (or more) points from at least 3 images, or 8 (or more) points from at least 2 images. Unlike previous approaches, the equations developed here lead to direct and linear solutions without going through the cameras' geometry. Our final linear shape computation uses all the available data  all points and all frames simultaneously: it uses a factorization of the matrix of invariant relations into 2 components of rank 4, a shape matrix and a coordinatesystem matrix."
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "The geometry of 1 point in N images under perspective projection has been thoroughly investigated, identifying bilinear, trilinear, and quadrilinear relations between the projections of 1 point in 2, 3 and 4 frames respectively. The dual problem  the geometry of N points in 1 image  has been studied mostly in the context of object recognition, often assuming weak perspective or affine projection. We provide here a complete description of this problem. We employ a formalism in which multiframe and multipoint geometries appear in symmetry: points and projections are interchangeable. We then derive bilinear equations for 6 points (dual to 4frame geometry), trilinear equations for 7 points (dual to 3frame geometry), and quadrilinear equations for 8 points (dual to the epipolar geometry). We show that the quadrilinear equations are dependent on the the [sic] bilinear and trilinear equations, and that adding more points will not generate any new equation. Applications to reconstruction and recognition: The new equations are used to design new algorithms for the reconstruction of shape from many frames, and for learning invariant relations for indexing into a database. We describe algorithms which require matching 6 (or more) corresponding points from at least 4 images, 7 (or more) points from at least 3 images, or 8 (or more) points from at least 2 images. Unlike previous approaches, the equations developed here lead to direct and linear solutions without going through the cameras' geometry. Our final linear shape computation uses all the available data  all points and all frames simultaneously: it uses a factorization of the matrix of invariant relations into 2 components of rank 4, a shape matrix and a coordinatesystem matrix."
Stability and likelihood of views of three dimensional objects by
Daphna Weinshall(
Book
)
2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Can we say anything general about the distribution of two dimensional views of general three dimensional objects? In this paper we present a first formal analysis of the stability and likelihood of two dimensional views (under weak perspective projection) of three dimensional objects. This analysis is useful for various aspects of object recognition and database indexing. Examples are Bayesian recognition and image interpretation; indexing to a three dimensional database by invariants of two dimensional images; the selection of 'good' templates that may reduce the complexity of correspondence between images and three dimensional objects; and ambiguity resolution using generic views. We show the following results: (1) Both the stability and likelihood of views do not depend on the particular distribution of points inside the object; they both depend on only three numbers, the three second moments of the object. (2) The most stable and the most likely views are the same view, which is the 'flattest' view of the object; moreover, there is no other view which is even locally the most stable or the most likely view. Under orthographic projection, we also show: (3) the distance between one image and another does not depend on the position of its viewpoint with respect to the object, it depends only on the (geodesic) distance between the viewpoints on the viewing sphere. We demonstrate these results with real and simulated data."
2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Can we say anything general about the distribution of two dimensional views of general three dimensional objects? In this paper we present a first formal analysis of the stability and likelihood of two dimensional views (under weak perspective projection) of three dimensional objects. This analysis is useful for various aspects of object recognition and database indexing. Examples are Bayesian recognition and image interpretation; indexing to a three dimensional database by invariants of two dimensional images; the selection of 'good' templates that may reduce the complexity of correspondence between images and three dimensional objects; and ambiguity resolution using generic views. We show the following results: (1) Both the stability and likelihood of views do not depend on the particular distribution of points inside the object; they both depend on only three numbers, the three second moments of the object. (2) The most stable and the most likely views are the same view, which is the 'flattest' view of the object; moreover, there is no other view which is even locally the most stable or the most likely view. Under orthographic projection, we also show: (3) the distance between one image and another does not depend on the position of its viewpoint with respect to the object, it depends only on the (geodesic) distance between the viewpoints on the viewing sphere. We demonstrate these results with real and simulated data."
Direct computation of 3D shape and motion invariants by
Daphna Weinshall(
Book
)
2 editions published between 1988 and 1989 in English and held by 2 WorldCat member libraries worldwide
2 editions published between 1988 and 1989 in English and held by 2 WorldCat member libraries worldwide
Three dimensional symmetry from two dimensional data by H Zabrodsky(
Book
)
2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide
Abstract: "In previous applications, bilateral symmetry of objects was used either as a descriptive feature in domains such as recognition and grasping, or as a way to reduce the complexity of structure from motion. In this paper we propose a novel application, using the symmetry property to 'symmetrize' data before and after reconstruction. We first show how to compute the closest symmetric 2D and 3D configurations given noisy data. This gives us a symmetrization procedure, which we apply to images before reconstruction, and which we apply to the 3D configuration after reconstruction. We demonstrate a significant improvement obtained with real images. We demonstrate the relative merits of symmetrization before and after reconstruction using simulated and real data."
2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide
Abstract: "In previous applications, bilateral symmetry of objects was used either as a descriptive feature in domains such as recognition and grasping, or as a way to reduce the complexity of structure from motion. In this paper we propose a novel application, using the symmetry property to 'symmetrize' data before and after reconstruction. We first show how to compute the closest symmetric 2D and 3D configurations given noisy data. This gives us a symmetrization procedure, which we apply to images before reconstruction, and which we apply to the 3D configuration after reconstruction. We demonstrate a significant improvement obtained with real images. We demonstrate the relative merits of symmetrization before and after reconstruction using simulated and real data."
Local shape approximation from shading by
Daphna Weinshall(
Book
)
1 edition published in 1991 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Shading can be used as an independent cue for exact shape recovery, or it can be used as a supplementary cue for shape interpolation between features, whose depth is known from other cues. Exact shape cannot be inferred from a local analysis of shading. However, for shape interpolation, a crude local approximation may be sufficient. This paper explores the limits of such local approximations that are easy to compute. In particular, the shape of shading is used to approximate the surface in areas of monotonic change of intensity. This analysis is complemented by a method to compute the direction of single point light source from the shading on occluding contours. A qualitative classification of shape near shading singularities is also discussed."
1 edition published in 1991 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Shading can be used as an independent cue for exact shape recovery, or it can be used as a supplementary cue for shape interpolation between features, whose depth is known from other cues. Exact shape cannot be inferred from a local analysis of shading. However, for shape interpolation, a crude local approximation may be sufficient. This paper explores the limits of such local approximations that are easy to compute. In particular, the shape of shading is used to approximate the surface in areas of monotonic change of intensity. This analysis is complemented by a method to compute the direction of single point light source from the shading on occluding contours. A qualitative classification of shape near shading singularities is also discussed."
Minimal decomposition of modelbased invariants, and applications to projective reconstruction and 3D recognition by
Daphna Weinshall(
Book
)
2 editions published in 1996 in English and held by 1 WorldCat member library worldwide
Abstract: "Modelbased invariants are relations between model parameters and image measurements, independent of the imaging parameters. Such relations are true for all images of the model. Here we describe an algorithm which, given L independent modelbased polynomial invariants describing some shape, will provide a linear reparameterization of the invariants. This reparameterization has the properties that: (i) it includes the minimal number of terms, and (ii) the shape terms are the same in all the modelbased invariants. This final representation has 2 main applications: (1) it gives us new representations of shape in terms of hyperplanes, which are convenient for object recognition; (2) it allows the design of new linear shape from motion algorithms."
2 editions published in 1996 in English and held by 1 WorldCat member library worldwide
Abstract: "Modelbased invariants are relations between model parameters and image measurements, independent of the imaging parameters. Such relations are true for all images of the model. Here we describe an algorithm which, given L independent modelbased polynomial invariants describing some shape, will provide a linear reparameterization of the invariants. This reparameterization has the properties that: (i) it includes the minimal number of terms, and (ii) the shape terms are the same in all the modelbased invariants. This final representation has 2 main applications: (1) it gives us new representations of shape in terms of hyperplanes, which are convenient for object recognition; (2) it allows the design of new linear shape from motion algorithms."
Dual computation of projective shape and camera positions from multiple images by
Svante Carlsson(
Book
)
2 editions published in 1996 in English and held by 1 WorldCat member library worldwide
Abstract: "Given multiple image data from a set of points in 3D, ther are two fundamental questions that can be addressed: What is the structure of the set of points in 3D? What are the positions of the cameras relative to the points? In this paper we show that, for projective views and with structure and position defined projectively, these problems are dual: the solutions to these problems are dual because they arise from constraint equations where space points and camera positions occur in a reciprocal way. More specifically, by using canonical reference frames for all points in space and images, the imaging of point sets in space by multiple cameras can be captured by constraint relations involving three different parameters only: (1) space points, (2) camera center points, (3) image points. The duality implies that the problem of computing camera positions from p points in n views can be solved with the same algorithm as the problem of directly reconstructing n + 4 points in p  4 views. This unifies different approaches to projective reconstruction: methods based on external calibration and direct methods exploiting constraints that exist between shape and image invariants."
2 editions published in 1996 in English and held by 1 WorldCat member library worldwide
Abstract: "Given multiple image data from a set of points in 3D, ther are two fundamental questions that can be addressed: What is the structure of the set of points in 3D? What are the positions of the cameras relative to the points? In this paper we show that, for projective views and with structure and position defined projectively, these problems are dual: the solutions to these problems are dual because they arise from constraint equations where space points and camera positions occur in a reciprocal way. More specifically, by using canonical reference frames for all points in space and images, the imaging of point sets in space by multiple cameras can be captured by constraint relations involving three different parameters only: (1) space points, (2) camera center points, (3) image points. The duality implies that the problem of computing camera positions from p points in n views can be solved with the same algorithm as the problem of directly reconstructing n + 4 points in p  4 views. This unifies different approaches to projective reconstruction: methods based on external calibration and direct methods exploiting constraints that exist between shape and image invariants."
Flexible syntactic matching of curves by
Yoram Gdalyahu(
)
1 edition published in 1998 in English and held by 1 WorldCat member library worldwide
1 edition published in 1998 in English and held by 1 WorldCat member library worldwide
From reference frames to reference planes : multiview parallax geometry and applications by
M BidjanIrani(
)
1 edition published in 1998 in English and held by 1 WorldCat member library worldwide
1 edition published in 1998 in English and held by 1 WorldCat member library worldwide
more
fewer
Audience Level
0 

1  
Kids  General  Special 
Related Identities
 Anemüller, Jörn Editor
 Gool, Luc van Thesis advisor Editor
 Massachusetts Institute of Technology Artificial Intelligence Laboratory
 Gool, Luc
 Whitaker College of Health Sciences, Technology, and Management Center for Biological Information Processing
 MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
 Edelman, Shimon Author
 Werman, Michael Author
 Whitaker College Center for Biological Information Processing
 Gdalyahu, Yoram Author
Associated Subjects
Artificial intelligence Automatic indexing Binocular vision Computer graphics Computer vision Curvature Depth perception Electronic circuitsNoise Engineering Geometrical constructions Geometry, Projective Image processing Image processingDigital techniques Incongruity Index theory (Mathematics) Machine learning Mental representation Multimedia systems Objectoriented databases Orthographic projection Pattern recognition systems Shades and shadows Surfaces Symmetry Universiṭat TelAviv Visual perception
Languages