Basri, Ronen
Overview
Works:  15 works in 34 publications in 1 language and 46 library holdings 

Roles:  Author 
Classifications:  Q335.M41, 
Publication Timeline
.
Most widely held works by
Ronen Basri
The alignment of objects with smooth surfaces by
Shimon Ullman(
Book
)
5 editions published between 1988 and 1991 in English and held by 5 WorldCat member libraries worldwide
This paper examines the recognition of rigid objects bounded by smooth surfaces, using an alignment approach. The projected image of such an object changes during rotation in a manner that is generally difficult to predict. An approach to this problem is suggested, using the 3D surface curvature at the points along the silhouette. The curvature information requires a single number for each point along the object's silhouette, the magnitude of the curvature vector at the point. We have implemented this method, and tested it on images of complex 3D objects. Models of the viewed objects were acquired using three images of each object. The implemented scheme was found to give accurate predictions of the objects' appearance for large transformations. Using this method, a small number of (viewercentered) models can be used to predict the new appearance of an object from any given viewpoint. (JHD)
5 editions published between 1988 and 1991 in English and held by 5 WorldCat member libraries worldwide
This paper examines the recognition of rigid objects bounded by smooth surfaces, using an alignment approach. The projected image of such an object changes during rotation in a manner that is generally difficult to predict. An approach to this problem is suggested, using the 3D surface curvature at the points along the silhouette. The curvature information requires a single number for each point along the object's silhouette, the magnitude of the curvature vector at the point. We have implemented this method, and tested it on images of complex 3D objects. Models of the viewed objects were acquired using three images of each object. The implemented scheme was found to give accurate predictions of the objects' appearance for large transformations. Using this method, a small number of (viewercentered) models can be used to predict the new appearance of an object from any given viewpoint. (JHD)
Determining the similarity of deformable shapes by Ronen Basri(
Book
)
2 editions published in 1998 in English and held by 4 WorldCat member libraries worldwide
Abstract: "Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not yet well understood, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e., articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches."
2 editions published in 1998 in English and held by 4 WorldCat member libraries worldwide
Abstract: "Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not yet well understood, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e., articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches."
Recognition by linear combinations of models by R Basri(
Book
)
2 editions published in 1989 in English and held by 4 WorldCat member libraries worldwide
2 editions published in 1989 in English and held by 4 WorldCat member libraries worldwide
Distance metric between 3D models and 2D images for recognition and classification by
Mekhon Ṿaitsman lemadaʻ(
Book
)
4 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."
4 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."
Paraperspective = Affine by Ronen Basri(
Book
)
1 edition published in 1994 in English and held by 3 WorldCat member libraries worldwide
Abstract: "It is shown that the set of all paraperspective images with arbitrary reference point and the set of affine images of a 3D object are identical. Consequently, all uncalibrated paraperspective images of an object can be constructed from a 3D model of the obeject by applying an affine transformation to the model and every affine image of the object represents some uncalibrated paraperspective image of the object. It follows that the paraperspective images of an object can be expressed as linear combinations of any two nondegenerate images of the object. When the image position of the reference point is given the parameters of the affine transformation (and, likewise, the coefficients of the linear combinations) satisfy two quadratic constraints. Conversely, when the values of parameters are given the image position of the reference point is determined by solving a biquadratic equation."
1 edition published in 1994 in English and held by 3 WorldCat member libraries worldwide
Abstract: "It is shown that the set of all paraperspective images with arbitrary reference point and the set of affine images of a 3D object are identical. Consequently, all uncalibrated paraperspective images of an object can be constructed from a 3D model of the obeject by applying an affine transformation to the model and every affine image of the object represents some uncalibrated paraperspective image of the object. It follows that the paraperspective images of an object can be expressed as linear combinations of any two nondegenerate images of the object. When the image position of the reference point is given the parameters of the affine transformation (and, likewise, the coefficients of the linear combinations) satisfy two quadratic constraints. Conversely, when the values of parameters are given the image position of the reference point is determined by solving a biquadratic equation."
Separation of transparent layers using focus by Yoav Y Schechner(
Book
)
3 editions published in 1997 in English and held by 3 WorldCat member libraries worldwide
3 editions published in 1997 in English and held by 3 WorldCat member libraries worldwide
Localization and positioning using combinations of model views by
Ehud Rivlin(
Book
)
3 editions published in 1992 in English and held by 3 WorldCat member libraries worldwide
Abstract: "A method for localization and positioning in an indoor environment is presented. Localization is the act of recognizing the environment, and positioning is the act of computing the exact coordinates of a robot in the environment. The method is based on representing the scene as a set of 2D views and predicting the appearance of novel views by linear combinations of the model views. The method accurately approximates the appearance of scenes under weakperspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases this approximation is sufficient to accurately describe the scene
3 editions published in 1992 in English and held by 3 WorldCat member libraries worldwide
Abstract: "A method for localization and positioning in an indoor environment is presented. Localization is the act of recognizing the environment, and positioning is the act of computing the exact coordinates of a robot in the environment. The method is based on representing the scene as a set of 2D views and predicting the appearance of novel views by linear combinations of the model views. The method accurately approximates the appearance of scenes under weakperspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases this approximation is sufficient to accurately describe the scene
Localization and homing using combinations of model views by R Basri(
Book
)
1 edition published in 1994 in English and held by 3 WorldCat member libraries worldwide
Abstract: "Navigation involves recognizing the environment, identifying the current position within the environment, and reaching particular positions. We present a method for localization (the act of recognizing the environment), positioning (the act of computing the exact coordinates of a robot in the environment), and homing (the act of returning to a previously visited position) from visual input. The method is based on representing the scene as a set of 2D views and predicting the appearances of novel views by linear combinations of the model views. The method accurately approximates the appearance of scenes under weak perspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases this approximation is sufficient to accurately describe the scene. When weakperspective approximation is invalid, either a larger number of models can be acquired or an iterative solution to account for the perspective distortions can be employed. The method has several advantages over other approaches. It uses relatively rich representations; the representations are 2D rather than 3D; and localization can be done from only a single 2D view without calibration. The same principal method is applied for both the localization and positioning problems, and a simple 'qualitative' algorithm for homing is derived from this method."
1 edition published in 1994 in English and held by 3 WorldCat member libraries worldwide
Abstract: "Navigation involves recognizing the environment, identifying the current position within the environment, and reaching particular positions. We present a method for localization (the act of recognizing the environment), positioning (the act of computing the exact coordinates of a robot in the environment), and homing (the act of returning to a previously visited position) from visual input. The method is based on representing the scene as a set of 2D views and predicting the appearances of novel views by linear combinations of the model views. The method accurately approximates the appearance of scenes under weak perspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases this approximation is sufficient to accurately describe the scene. When weakperspective approximation is invalid, either a larger number of models can be acquired or an iterative solution to account for the perspective distortions can be employed. The method has several advantages over other approaches. It uses relatively rich representations; the representations are 2D rather than 3D; and localization can be done from only a single 2D view without calibration. The same principal method is applied for both the localization and positioning problems, and a simple 'qualitative' algorithm for homing is derived from this method."
Recognition by Linear Combination of Models by
Shimon Ullman(
Book
)
2 editions published in 1989 in English and held by 2 WorldCat member libraries worldwide
Visual object recognition requires the matching of an image with a set of models stored in memory. In this paper we propose an approach to recognition in which a 3D object is represented by the linear combination of 2D images of the object. If M is the set of pictures representing a given object, and P is the 2D image of an object to be recognized, then P is considered an instance of M if P for some constants. We show that this approach handles correctly rigid 3D transformations of objects with sharp as well as smooth boundaries, and can also handle nonrigid transformations. The paper is divided into two parts. In the first part we show that the variety of views depicting the same object under different transformations can often be expressed as the linear combinations of a small number of views. In the second part we suggest how this linear combination property may be used in the recognition process
2 editions published in 1989 in English and held by 2 WorldCat member libraries worldwide
Visual object recognition requires the matching of an image with a set of models stored in memory. In this paper we propose an approach to recognition in which a 3D object is represented by the linear combination of 2D images of the object. If M is the set of pictures representing a given object, and P is the 2D image of an object to be recognized, then P is considered an instance of M if P for some constants. We show that this approach handles correctly rigid 3D transformations of objects with sharp as well as smooth boundaries, and can also handle nonrigid transformations. The paper is divided into two parts. In the first part we show that the variety of views depicting the same object under different transformations can often be expressed as the linear combinations of a small number of views. In the second part we suggest how this linear combination property may be used in the recognition process
On the uniqueness of correspondence under orthographic and perspective projections by Ronen Basri(
Book
)
2 editions published in 1991 in English and held by 2 WorldCat member libraries worldwide
In all these cases corresponding points lie along epipolar lines, and these lines can be recovered from a small set of corresponding points. In the second part of the paper we discuss the potential use of epipolar lines in the matching process. We present an algorithm that recovers the correspondence from three contour images. The algorithm was implemented and used to construct object models for recognition. In addition we discuss how epipolar lines can be used to solve the aperture problem."
2 editions published in 1991 in English and held by 2 WorldCat member libraries worldwide
In all these cases corresponding points lie along epipolar lines, and these lines can be recovered from a small set of corresponding points. In the second part of the paper we discuss the potential use of epipolar lines in the matching process. We present an algorithm that recovers the correspondence from three contour images. The algorithm was implemented and used to construct object models for recognition. In addition we discuss how epipolar lines can be used to solve the aperture problem."
Extracting salient curves from images : an analysis of the saliency network by Tao D Alter(
Book
)
2 editions published between 1995 and 1996 in English and held by 2 WorldCat member libraries worldwide
Abstract: "The Saliency Network proposed by Shashua and Ullman is a wellknown approach to the problem of extracting salient curves from images while performing gap completion. This paper analyzes the Saliency Network. The Saliency Network is attractive for several reasons. First, the network generally prefers long and smooth curves over short or wiggly ones. While computing saliencies, the network also fills in gaps with smooth completions and tolerates noise. Finally, the network is locally connected, and its size is proportional to the size of the image. Nevertheless, our analysis reveals certain weaknesses with the method. In particular, we show cases in which the most salient element does not lie on the perceptually most salient curve. Furthermore, in some cases the saliency measure changes its preferences when curves are scaled uniformly. Also, we show that for certain fragmented curves the measure prefers large gaps over a few small gaps of the same total size. In addition, we analyze the time complexity required by the method. We show that the number of steps required for convergence in serial implementations is quadratic in the size of the network, and in parallel implementations is linear in the size of the network. We discuss problems due to coarse sampling of the range of possible orientations. We show that with proper sampling the complexity of the network becomes at least cubic in the size of the network. Finally, we consider the possibility of using the Saliency Network for grouping. We show that the Saliency Network recovers the most salient curve efficiently, but it has problems with identifying any salient curve other than the most salient one."
2 editions published between 1995 and 1996 in English and held by 2 WorldCat member libraries worldwide
Abstract: "The Saliency Network proposed by Shashua and Ullman is a wellknown approach to the problem of extracting salient curves from images while performing gap completion. This paper analyzes the Saliency Network. The Saliency Network is attractive for several reasons. First, the network generally prefers long and smooth curves over short or wiggly ones. While computing saliencies, the network also fills in gaps with smooth completions and tolerates noise. Finally, the network is locally connected, and its size is proportional to the size of the image. Nevertheless, our analysis reveals certain weaknesses with the method. In particular, we show cases in which the most salient element does not lie on the perceptually most salient curve. Furthermore, in some cases the saliency measure changes its preferences when curves are scaled uniformly. Also, we show that for certain fragmented curves the measure prefers large gaps over a few small gaps of the same total size. In addition, we analyze the time complexity required by the method. We show that the number of steps required for convergence in serial implementations is quadratic in the size of the network, and in parallel implementations is linear in the size of the network. We discuss problems due to coarse sampling of the range of possible orientations. We show that with proper sampling the complexity of the network becomes at least cubic in the size of the network. Finally, we consider the possibility of using the Saliency Network for grouping. We show that the Saliency Network recovers the most salient curve efficiently, but it has problems with identifying any salient curve other than the most salient one."
Recognition using region correspondences by R Basri(
Book
)
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Recogniton systems attempt to recover information about the identity of the observed objects and their location in the environment. A fundamental problem in recognition is the following. Given a correspondence between some portions of an object model and some portions of an image, determine whether the image contains an instance of the object, and, in case it does, determine the transformation that relates the model to the image. The current approaches to this problem are divided into methods that use 'global' properties of the object (e.g., centroid and moments of inertia) and methods that use 'local' properties of the object (e.g., corners and line segments). Global properties are sensitive to occlusion and, specifically, to self occlusion. Local properties are difficult to locate reliably, and their matching involves intensive computation. A novel method for recognition that uses region information is presented. In our approach the model is divided into volumes, and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similiarity, affine, and projective transformations and to projections of 3D objects undergoing affine and projective transformations. The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls. Like the global methods, our approach makes use of region information that reflects the true shape of the object. But like local methods, our approach can handle occlusion."
1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Recogniton systems attempt to recover information about the identity of the observed objects and their location in the environment. A fundamental problem in recognition is the following. Given a correspondence between some portions of an object model and some portions of an image, determine whether the image contains an instance of the object, and, in case it does, determine the transformation that relates the model to the image. The current approaches to this problem are divided into methods that use 'global' properties of the object (e.g., centroid and moments of inertia) and methods that use 'local' properties of the object (e.g., corners and line segments). Global properties are sensitive to occlusion and, specifically, to self occlusion. Local properties are difficult to locate reliably, and their matching involves intensive computation. A novel method for recognition that uses region information is presented. In our approach the model is divided into volumes, and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similiarity, affine, and projective transformations and to projections of 3D objects undergoing affine and projective transformations. The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls. Like the global methods, our approach makes use of region information that reflects the true shape of the object. But like local methods, our approach can handle occlusion."
Constancy and similarity by Ronen Basri(
Book
)
1 edition published in 1996 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Pizlo, Rosenfeld, and Weiss[6] suggest that people perceive two 2D shapes as the same (i.e., there is shape constancy) when one shape might be a perspective image of the other. We argue that this hypothesis is both too broad and too restrictive. Their view is too broad because, as we show, two such images can appear quite different when there is significant perspective distortion. Their view is too restrictive because factors such as context and the complexity of the shapes compared can play a role in judgements of shape constancy. Moreover, Pizlo et al.'s formulation is asymmetric in requiring that one of the images be considered the model which produces the other. One can consider removing this asymmetry by judging shapes as the same when they could be two perspective views, taken with the same camera, of a third planar shape. We show that this is true if and only if the images are projectively equivalent. However, Pizlo et al. have convincingly rejected projective equivalence as a model of shape constancy."
1 edition published in 1996 in English and held by 2 WorldCat member libraries worldwide
Abstract: "Pizlo, Rosenfeld, and Weiss[6] suggest that people perceive two 2D shapes as the same (i.e., there is shape constancy) when one shape might be a perspective image of the other. We argue that this hypothesis is both too broad and too restrictive. Their view is too broad because, as we show, two such images can appear quite different when there is significant perspective distortion. Their view is too restrictive because factors such as context and the complexity of the shapes compared can play a role in judgements of shape constancy. Moreover, Pizlo et al.'s formulation is asymmetric in requiring that one of the images be considered the model which produces the other. One can consider removing this asymmetry by judging shapes as the same when they could be two perspective views, taken with the same camera, of a third planar shape. We show that this is true if and only if the images are projectively equivalent. However, Pizlo et al. have convincingly rejected projective equivalence as a model of shape constancy."
Localization and homing using combinations of model views by Ronen Basri(
)
1 edition published in 1995 in English and held by 1 WorldCat member library worldwide
1 edition published in 1995 in English and held by 1 WorldCat member library worldwide
Recognition by prototypes by
Mekhon Ṿaitsman lemadaʻ(
Book
)
4 editions published between 1992 and 1995 in English and held by 1 WorldCat member library worldwide
Abstract: "A scheme for recognizing 3D objects from single 2D images is introduced. The scheme proceeds in two stages. In the first stage, the categorization stage, the image is compared to prototype objects. For each prototype, the view that most resembles the image is recovered, and, if the view is found to be similar to the image, the class identity of the object is determined. In the second stage, the identification stage, the observed object is compared to the individual models of its class, where classes are expected to contain objects with relatively similar shapes. For each model, a view that matches the image is sought. If such a view is found, the object's specific identity is determined
4 editions published between 1992 and 1995 in English and held by 1 WorldCat member library worldwide
Abstract: "A scheme for recognizing 3D objects from single 2D images is introduced. The scheme proceeds in two stages. In the first stage, the categorization stage, the image is compared to prototype objects. For each prototype, the view that most resembles the image is recovered, and, if the view is found to be similar to the image, the class identity of the object is determined. In the second stage, the identification stage, the observed object is compared to the individual models of its class, where classes are expected to contain objects with relatively similar shapes. For each model, a view that matches the image is sought. If such a view is found, the object's specific identity is determined
more
fewer
Audience Level
0 

1  
Kids  General  Special 
Related Identities
 Massachusetts Institute of Technology Artificial Intelligence Laboratory
 Ullman, Shimon Author
 MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
 Rivlin, Ehud Author
 Weinshall, Daphna
 Ehud, Rivlin
 Jacobs, David
 Kiryati, Nahum
 Ṭekhniyon, Makhon ṭekhnologi leYiśraʼel Center for Communication and Information Technologies
 Alter, Tao D. Author
Languages