Ullman, Shimon
Overview
Works:  54 works in 161 publications in 2 languages and 2,639 library holdings 

Genres:  Conference papers and proceedings 
Roles:  Author, Editor, Other 
Classifications:  BF241, 152.14 
Publication Timeline
.
Most widely held works by
Shimon Ullman
Highlevel vision : object recognition and visual cognition by
Shimon Ullman(
Book
)
27 editions published between 1995 and 2001 in English and held by 603 WorldCat member libraries worldwide
27 editions published between 1995 and 2001 in English and held by 603 WorldCat member libraries worldwide
The interpretation of visual motion by
Shimon Ullman(
Book
)
26 editions published between 1977 and 1985 in 3 languages and held by 585 WorldCat member libraries worldwide
26 editions published between 1977 and 1985 in 3 languages and held by 585 WorldCat member libraries worldwide
Proceedings of the 12th IAPR International Conference on Pattern Recognition : October 913, 1994, Jerusalem, Israel by
International Conference on Pattern Recognition(
Book
)
6 editions published in 1994 in English and held by 86 WorldCat member libraries worldwide
6 editions published in 1994 in English and held by 86 WorldCat member libraries worldwide
Image understanding : 198586 by W Richards(
Book
)
4 editions published between 1986 and 1987 in English and held by 50 WorldCat member libraries worldwide
4 editions published between 1986 and 1987 in English and held by 50 WorldCat member libraries worldwide
Image understanding : 1989 by
Shimon Ullman(
Book
)
5 editions published between 1990 and 1991 in English and held by 33 WorldCat member libraries worldwide
5 editions published between 1990 and 1991 in English and held by 33 WorldCat member libraries worldwide
Image understanding 1984(
Book
)
6 editions published between 1984 and 1985 in English and held by 9 WorldCat member libraries worldwide
6 editions published between 1984 and 1985 in English and held by 9 WorldCat member libraries worldwide
Visual routines by
Shimon Ullman(
Book
)
7 editions published between 1980 and 1983 in English and Undetermined and held by 7 WorldCat member libraries worldwide
7 editions published between 1980 and 1983 in English and Undetermined and held by 7 WorldCat member libraries worldwide
Image understanding 19851986(
Book
)
1 edition published in 1987 in English and held by 6 WorldCat member libraries worldwide
1 edition published in 1987 in English and held by 6 WorldCat member libraries worldwide
On visual detection of light sources by
Shimon Ullman(
Book
)
4 editions published in 1975 in English and Undetermined and held by 6 WorldCat member libraries worldwide
The paper addresses the following problem: Given an array of light intensities obtained from some scene, find the light sources in the original scene. The following factors are discussed from the point of view of their relevance to light sources detection: The highest intensity in the scene, absolute intensity value, local and global contrast, comparison with the average intensity, and lightness computation. They are shown to be insufficient for explaining humans' ability to identify light sources in their visual field. Finally, a method for accomplishing the source detection task in the mondrian world is presented
4 editions published in 1975 in English and Undetermined and held by 6 WorldCat member libraries worldwide
The paper addresses the following problem: Given an array of light intensities obtained from some scene, find the light sources in the original scene. The following factors are discussed from the point of view of their relevance to light sources detection: The highest intensity in the scene, absolute intensity value, local and global contrast, comparison with the average intensity, and lightness computation. They are shown to be insufficient for explaining humans' ability to identify light sources in their visual field. Finally, a method for accomplishing the source detection task in the mondrian world is presented
Image understanding(
Book
)
3 editions published between 1984 and 1990 in English and held by 6 WorldCat member libraries worldwide
3 editions published between 1984 and 1990 in English and held by 6 WorldCat member libraries worldwide
A modeldriven geometry theorem prover by
Shimon Ullman(
Book
)
2 editions published in 1975 in English and held by 6 WorldCat member libraries worldwide
This paper describes a new Geometry Theorem Prover, which was implemented to illuminate some issues related to the use of models in theorem proving. The paper is divided into three parts: Part 1 describes the G.T.P. and presents the ideas embedded in it. Part 2 describes the backward search mechanism. Part 3 addresses the notion of similarity in a problem, defines a notion of semantic symmetry, and compares it to Gelernter's concept of syntactic symmetry
2 editions published in 1975 in English and held by 6 WorldCat member libraries worldwide
This paper describes a new Geometry Theorem Prover, which was implemented to illuminate some issues related to the use of models in theorem proving. The paper is divided into three parts: Part 1 describes the G.T.P. and presents the ideas embedded in it. Part 2 describes the backward search mechanism. Part 3 addresses the notion of similarity in a problem, defines a notion of semantic symmetry, and compares it to Gelernter's concept of syntactic symmetry
Limitations of non modelbased recognition schemes by
Massachusetts Institute of Technology(
Book
)
3 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide
Different approaches to visual object recognition can be divided into two general classes: modelbased vs. non modelbased schemes. In this paper we establish some limitation on the class of non modelbased recognition schemes. a non modelbased scheme is based on functions invariant to viewing position and illumination conditions. We show that every function that is invariant to viewing position of all objects is the trivial (constant) function. The same result holds even if the recognition function is not required to be perfect, but is allowed to make mistakes and misidentify each object from a substantial fraction of viewing directions. It follows that every consistent recognition scheme for recognizing Three dimensional objects must in general be model based. We then consider recognition schemes restricted to classes of objects and show that, for some classes, the only consistent recognition function is still the trivial function. For other classes (such as the class of symmetric objects) a nontrivial recognition scheme exists. We define the notion of a discrimination power of a consistent recognition function for a class of objects. The function's discrimination power determines the set of objects that can be discriminated by the recognition function. We show that it is possible to determine the upper bound of the function's discrimination power for every consistent recognition function
3 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide
Different approaches to visual object recognition can be divided into two general classes: modelbased vs. non modelbased schemes. In this paper we establish some limitation on the class of non modelbased recognition schemes. a non modelbased scheme is based on functions invariant to viewing position and illumination conditions. We show that every function that is invariant to viewing position of all objects is the trivial (constant) function. The same result holds even if the recognition function is not required to be perfect, but is allowed to make mistakes and misidentify each object from a substantial fraction of viewing directions. It follows that every consistent recognition scheme for recognizing Three dimensional objects must in general be model based. We then consider recognition schemes restricted to classes of objects and show that, for some classes, the only consistent recognition function is still the trivial function. For other classes (such as the class of symmetric objects) a nontrivial recognition scheme exists. We define the notion of a discrimination power of a consistent recognition function for a class of objects. The function's discrimination power determines the set of objects that can be discriminated by the recognition function. We show that it is possible to determine the upper bound of the function's discrimination power for every consistent recognition function
A model for the spatiotemporal organization of X and Y type ganglion cells in the primate retina by J Richter(
Book
)
2 editions published between 1980 and 1981 in English and held by 5 WorldCat member libraries worldwide
2 editions published between 1980 and 1981 in English and held by 5 WorldCat member libraries worldwide
Recognizing solid objects by alignment with an image by
Daniel P Huttenlocher(
Book
)
2 editions published in 1989 in English and held by 5 WorldCat member libraries worldwide
We have implemented a recognition system that uses this transformation method to determine possible alignments of a model with an image. Each of these hypothesized matches is verified by comparing the entire edge contours of the aligned object with the image edges. Using the entire edge contours for verification, rather than a few local feature points, reduces the chance of finding false matches. The system has been tested on partly occluded objects in highly cluttered scenes."
2 editions published in 1989 in English and held by 5 WorldCat member libraries worldwide
We have implemented a recognition system that uses this transformation method to determine possible alignments of a model with an image. Each of these hypothesized matches is verified by comparing the entire edge contours of the aligned object with the image edges. Using the entire edge contours for verification, rather than a few local feature points, reduces the chance of finding false matches. The system has been tested on partly occluded objects in highly cluttered scenes."
The measurement of visual motion by
Ellen Catherine Hildreth(
Book
)
4 editions published in 1982 in English and held by 5 WorldCat member libraries worldwide
The analysis of visual motion divides naturally into two stages: the first is the measurement of motion, for example, the assignment of direction and magnitude of velocity to elements in the image, on the basis of the changing intensity pattern; the second is the use of motion measurements, for example, to separate the scene into distinct objects, and infer their threedimensional structure. In this paper, we present a computational study of the measurement of motion. Similar to other visual processes, the motion of elements is not determined uniquely by information in the changing image; additional constraint is required to compute a unique velocity filed. Given this global ambiguity of motion. Local measurements from the changing image, such as those provided by directionallyselective simple cells in primate visual cortex, cannot possibly specify a unique local velocity vector, and in fact, specify only one component of velocity. Computation of the full twodimensional velocity field requires the integration of local motion measurements, either over an area, or along contours in the image. We will examine possible algorithms for computing motion, based on a range of additional constraints. Finally, we will present implications for the biological computation of motion
4 editions published in 1982 in English and held by 5 WorldCat member libraries worldwide
The analysis of visual motion divides naturally into two stages: the first is the measurement of motion, for example, the assignment of direction and magnitude of velocity to elements in the image, on the basis of the changing intensity pattern; the second is the use of motion measurements, for example, to separate the scene into distinct objects, and infer their threedimensional structure. In this paper, we present a computational study of the measurement of motion. Similar to other visual processes, the motion of elements is not determined uniquely by information in the changing image; additional constraint is required to compute a unique velocity filed. Given this global ambiguity of motion. Local measurements from the changing image, such as those provided by directionallyselective simple cells in primate visual cortex, cannot possibly specify a unique local velocity vector, and in fact, specify only one component of velocity. Computation of the full twodimensional velocity field requires the integration of local motion measurements, either over an area, or along contours in the image. We will examine possible algorithms for computing motion, based on a range of additional constraints. Finally, we will present implications for the biological computation of motion
Fillingin the gaps : the shape of subjective contours and a model for their generation by
Shimon Ullman(
Book
)
3 editions published in 1976 in English and Undetermined and held by 5 WorldCat member libraries worldwide
The properties of isotropy, smoothness, minimum curvature and locality suggest the shape of filledin contours between two boundary edges. The contours are composed of the arcs of two circles tangent to the given edges, meeting smoothly, and minimizing the total curvature. It is shown that shapes meeting all the above requirements can be generated by a network which performs simple, local computations. It is suggested that the fillingin process plays an important role in the early processing of visual information. (Author)
3 editions published in 1976 in English and Undetermined and held by 5 WorldCat member libraries worldwide
The properties of isotropy, smoothness, minimum curvature and locality suggest the shape of filledin contours between two boundary edges. The contours are composed of the arcs of two circles tangent to the given edges, meeting smoothly, and minimizing the total curvature. It is shown that shapes meeting all the above requirements can be generated by a network which performs simple, local computations. It is suggested that the fillingin process plays an important role in the early processing of visual information. (Author)
The computational study of vision by
Ellen Catherine Hildreth(
Book
)
4 editions published in 1988 in English and Undetermined and held by 5 WorldCat member libraries worldwide
Through vision, we derive a rich understanding of what is in the world, where objects are located, and how they are changing with time. Because we obtain this understanding immediately, effortlessly, and without conscious introspection, we can be deceived into thinking that vision should therefore be a fairly simple task to perform. The computational approach to the study of vision inquires directly into the sort of information processing needed to extract important information from the changing visual image  information such as the threedimensional (3D) structure and movement of objects in the scene, or the color and texture of object surfaces. An important contribution that computational studies have made is to show how difficult vision is to perform, and how complex are the processes needed to perform visual tasks successfully. This article reviews some computational studies of vision, focusing on edge detection, binocular stereo, motion analysis, intermediate vision and object recognition. Keywords: Computer vision; Vision; Binocular stereo vision; Motion analysis; Object recognition; Pattern recognition. (KT)
4 editions published in 1988 in English and Undetermined and held by 5 WorldCat member libraries worldwide
Through vision, we derive a rich understanding of what is in the world, where objects are located, and how they are changing with time. Because we obtain this understanding immediately, effortlessly, and without conscious introspection, we can be deceived into thinking that vision should therefore be a fairly simple task to perform. The computational approach to the study of vision inquires directly into the sort of information processing needed to extract important information from the changing visual image  information such as the threedimensional (3D) structure and movement of objects in the scene, or the color and texture of object surfaces. An important contribution that computational studies have made is to show how difficult vision is to perform, and how complex are the processes needed to perform visual tasks successfully. This article reviews some computational studies of vision, focusing on edge detection, binocular stereo, motion analysis, intermediate vision and object recognition. Keywords: Computer vision; Vision; Binocular stereo vision; Motion analysis; Object recognition; Pattern recognition. (KT)
Computational studies in the interpretation of structure and motion : summary and extension by
Shimon Ullman(
Book
)
3 editions published in 1983 in English and held by 4 WorldCat member libraries worldwide
Computational studies of the interpretation of structure from notion examine the conditions under which threedimensional structure can be recovered from motion in the image. The first part of this paper summarizes the main results obtained to date in these studies. The second part examines two issues: the robustness of the 3D interpretation of perspective velocity fields, and the 3D information contained in orthographic velocity fields. The two are related because, under local analysis, limitations on the interpretation of orthographic velocity fields also apply to perspective projection. The following results are established: When the interpretation is applied locally, the 3D interpretation of the perspective velocity field is unstable; The orthographic velocity field determines the structure of the inducing object exactly up to a depthscaling; For planar objects, the orthographic velocity field always admits two distinct solutions up to depthscaling; and The 3D structure is determined uniquely by a view and a half of the orthographic velocity field. (Author)
3 editions published in 1983 in English and held by 4 WorldCat member libraries worldwide
Computational studies of the interpretation of structure from notion examine the conditions under which threedimensional structure can be recovered from motion in the image. The first part of this paper summarizes the main results obtained to date in these studies. The second part examines two issues: the robustness of the 3D interpretation of perspective velocity fields, and the 3D information contained in orthographic velocity fields. The two are related because, under local analysis, limitations on the interpretation of orthographic velocity fields also apply to perspective projection. The following results are established: When the interpretation is applied locally, the 3D interpretation of the perspective velocity field is unstable; The orthographic velocity field determines the structure of the inducing object exactly up to a depthscaling; For planar objects, the orthographic velocity field always admits two distinct solutions up to depthscaling; and The 3D structure is determined uniquely by a view and a half of the orthographic velocity field. (Author)
The alignment of objects with smooth surfaces by
Shimon Ullman(
Book
)
3 editions published in 1988 in English and held by 4 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 difficult to predict. A method to approach 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 and tested this method on images of complex 3D objects; it was found to give accurate predictions of the objects' appearances for large transformations. A small number of models can be used to predict the new appearance of an object from any viewpoint
3 editions published in 1988 in English and held by 4 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 difficult to predict. A method to approach 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 and tested this method on images of complex 3D objects; it was found to give accurate predictions of the objects' appearances for large transformations. A small number of models can be used to predict the new appearance of an object from any viewpoint
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
more
fewer
Audience Level
0 

1  
Kids  General  Special 
Related Identities
 Peleg, Shmuel Editor
 International Association for Pattern Recognition
 Richards, Whitman Other Editor
 Massachusetts Institute of Technology Artificial Intelligence Laboratory
 MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
 Basri, Ronen Author
 Moses, Yael Author
 Marr, David Author
 Hildreth, Ellen Catherine Author
 Richter, J. Author
Useful Links
Associated Subjects
Artificial intelligence Artificial intelligenceData processing Automatic theorem proving Binocular vision Cognition Computer vision Digital computer simulation Form perception Image processing Image processingDigital techniques Imaging systems Light Motion perception (Vision) Motion perception (Vision)Data processing Optical data processing Pattern perception Pattern recognition systems Programming (Mathematics) Surfaces Vision Visual perception Visual perceptionData processing