Behrooz Kamgar-Parsi - Academia.edu (original) (raw)

Papers by Behrooz Kamgar-Parsi

Biological Cybernetics, 1990

... Behzad Kamgar-Parsi 1 and Behrooz Kamgar-Parsi 2 1 Center for Automation Research, University... more ... Behzad Kamgar-Parsi 1 and Behrooz Kamgar-Parsi 2 1 Center for Automation Research, University of Maryland, College Park, MD 20742, USA 2 Center for Applied Research in Artificial Intelligence, Naval Research Laboratory, Washington, DC ... E=AE B 2 x EZ VxYx~+ VxYr~ ...

Formal Aspects of Computing, 1990

In target recognition in uncontrolled environments the test target may not belong to the prestore... more In target recognition in uncontrolled environments the test target may not belong to the prestored targets or target classes. Hence, in such environments the use of a typical classifier which finds the closest class still leaves open the question of whether the test target truly belongs to that class. To decide whether a test target matches a stored target, common

Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition, 1988

A moving rigid object produces a moving image on the retina of an observer. It is shown that only... more A moving rigid object produces a moving image on the retina of an observer. It is shown that only the first-order spatial derivatives of image motion are sufficient to determine (i) the maximum and minimum time-to-collision of the observer and the object and (ii) the maximum and minimum angular velocity of the object along the direction of view. The second or higher order derivatives whose estimation is expensive and unreliable are not necessary. (The second-order derivatives are necessary to determine the actual motion of the object.) These results are interpreted in the image domain in terms of three differentiul invuriants of the image flow field: divergence, curl, and shear magnitude. In the world domain. the above results are interpreted in terms of the motion and local surface orientation of the object. In particular, the result that the minimum time-to-collision could be determined from only the first-order derivatives has a fundamental significance to both biological and machine vision systems. It implies that an organism (or a robot) can quickly respond to avoid collision with a moving object from only coarse information. This capability exists irrespective of the shape or motion of the object. The only restriction is that motion should be rigid.

AIAA Guidance, Navigation and Control Conference and Exhibit, 2007

2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems, 2007

proposed an approach for capturing a human similarity measure within a classifier, e.g., an artif... more proposed an approach for capturing a human similarity measure within a classifier, e.g., an artificial neural network, for face recognition. This is done by automatically generating and labeling arbitrarily large sets of morphed images (typically tens of thousands) in agreement with a human critic. One set is composed of images with reduced resemblance to the imaged person, yet recognizable by humans as that person (positive exemplars); the second set consists of images with some resemblance to the imaged person, but not enough to be recognizable as that person (negative exemplars). For each person of interest, a dedicated classifier is developed. From a practical point of view, it appears that the most challenging aspect of that approach is to completely enclose the decision region belonging to the person of interest. Because of the high dimensionality of the huamn face space, this is not simple matter especially for certain subjects. In this paper, we propose a new operator that morphs the image of the target person away from those of others. The new operator when applied together with the previous operator (morphing toward) helps to close the constructed decision region. Also, in this paper we propose the utilization of two networks for each target person; the added network covers not just the eyes and nose, but practically the entire face though in a coarse fashion. The second network, FaceNet, screens images before they are presented to the first network, EyeNet. The new developments have reduced the false accept rate by orders of magnitude with minimal impact on false reject rate. It now appreas, more than before, that the following important and long desired goal is within reach: "The similarity measure used in a face recognition system should be designed so that humans' ability to perform face recognition and recall are imitated as closely as possible by the machine [5]".

Computer Vision, Graphics, and Image Processing, 1990

It is a simple problem to fit one line to a collection of points in the plane. But when the probl... more It is a simple problem to fit one line to a collection of points in the plane. But when the problem is generalized to two or more lines then the problem complexity becomes exponential in the number of points because we must decide on a partitioning of the points among the lines they are to fit. The same is true for fitting lines to points in three-dimensional space or hyperplanes to data points of high dimensions. We show that this problem despite its exponential complexity can be formulated as an optimization problem for which very good, but not necessarily optimal, solutions can be found by using an artificial neural network. Furthermore, we show that given a tolerance one can determine the number of lines (or planes) that should be fitted to a given point configuration. This problem is prototypical of a class of problems in computer vision, pattern recognition, and data fitting. For example, the method we propose can be used in reconstructing a planar world from range data or in recognizing point patterns in an image.

Lecture Notes in Computer Science, 2004

Current appearance-based face recognition system encounters the difficulty to recognize faces wit... more Current appearance-based face recognition system encounters the difficulty to recognize faces with appearance variations, while only a small number of training images are available. We present a scheme based on the analysis by synthesis framework. A 3D generic face model is aligned onto a given frontal face image. A number of synthetic face images are generated with appearance variations from the aligned 3D face model. These synthesized images are used to construct an affine subspace for each subject. Training and test images for each subject are represented in the same way in such a subspace. Face recognition is achieved by minimizing the distance between the subspace of a test subject and that of each subject in the database. Only a single face image of each subject is available for training in our experiments. Preliminary experimental results are promising.

Biometric Technology for Human Identification VII, 2010

We report the development of a face recognition system which operates in the same way as humans i... more We report the development of a face recognition system which operates in the same way as humans in that it is capable of recognizing a number of people, while rejecting everybody else as strangers. While humans do it routinely, a particularly challenging aspect of the problem ...

Applications and Science of Artificial Neural Networks, 1995

ABSTRACT

Advanced Sciences and Technologies for Security Applications, 2006

Page 1. 14 The Use of Synthetic Data in Eye/Face Recognition Behrooz Kamgar-Parsi,1 Behzad Kamgar... more Page 1. 14 The Use of Synthetic Data in Eye/Face Recognition Behrooz Kamgar-Parsi,1 Behzad Kamgar-Parsi,2 and Benjamin N. Waber1,3 1Information Technology Division, Naval Research Laboratory, Washington, DC 20375 ...

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

Existing algorithms for finding the best match between two sets of 3D lines are not completely sa... more Existing algorithms for finding the best match between two sets of 3D lines are not completely satisfactory in the sense that they either yield approximate solutions, or are iterative which means they may not converge to the globally optimal solution. An even more serious shortcoming of the existing algorithms is that they are all non-invariant with respect to the translation

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 1999

The problem of screening images of the skies to determine whether they contain aircraft or not is... more The problem of screening images of the skies to determine whether they contain aircraft or not is both of theoretical and practical interest. After the most prominent visual signal in the infrared image of the sky is extracted, the question is whether the signal is a correct match of an aircraft. Common approaches calculate the degree of similarity of the

2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, 2006

required to rank face/facial images (as a precursor to recognition). Upon encounter, they recogni... more required to rank face/facial images (as a precursor to recognition). Upon encounter, they recognize the face or reject it as We propose an approach for capturing a human similarity unaila or pehp'sntbigtepro en ogt measure (within an artificial neural network, SVM, or other classifiers) for face recognition. That is, the following impor-

Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), 1999

Image understanding often involves object recognition, where a basic question is how to decide wh... more Image understanding often involves object recognition, where a basic question is how to decide whether a match is correct. Typically the best match (among a set of prestored objects) is assumed to be the correct match. This may work well in controlled environments (closed world). But, in uncontrolled environments (open world), the test object may not belong to the prestored

Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

Methods for matching sets of 3D lines depend on whether line lengths are finite or infinite. In t... more Methods for matching sets of 3D lines depend on whether line lengths are finite or infinite. In terms of line lengths, three basic cases arise in matching sets of lines: (1) finite to finite, (2) finite to infinite, and (3) infinite to infinite. For cases 1 and 2, which have not been treated in the literature, we present convergent iterative

Unmanned Ground Vehicle Technology, 1999

ABSTRACT

CVPR 2011, 2011

We revisit the problem of matching a set of lines in the 2D image to a set of corresponding lines... more We revisit the problem of matching a set of lines in the 2D image to a set of corresponding lines in the 3D model for the following reasons. (a) Existing algorithms that treat lines as innitely long contain a aw, namely, the solutions found are not invariant with respect to the choice of the coordinate frame. The source of this

Proceedings of International Conference on Image Processing, 1997

ABSTRACT

Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001

Object extraction from an IR image background is of great interest both to the military and the c... more Object extraction from an IR image background is of great interest both to the military and the commercial sector. A convenient and popular approach to object extraction is image thresholding. In this paper, we describe a new and easy to implement approach for extracting object(s) in single frame IR images, which has many similarities to image thresholding. Both on the basis of theoretical considerations and experimental results, however, our approach appears to be noticeably more dependable than image thresholding for IR images

Biological Cybernetics, 1990

... Behzad Kamgar-Parsi 1 and Behrooz Kamgar-Parsi 2 1 Center for Automation Research, University... more ... Behzad Kamgar-Parsi 1 and Behrooz Kamgar-Parsi 2 1 Center for Automation Research, University of Maryland, College Park, MD 20742, USA 2 Center for Applied Research in Artificial Intelligence, Naval Research Laboratory, Washington, DC ... E=AE B 2 x EZ VxYx~+ VxYr~ ...

Formal Aspects of Computing, 1990

In target recognition in uncontrolled environments the test target may not belong to the prestore... more In target recognition in uncontrolled environments the test target may not belong to the prestored targets or target classes. Hence, in such environments the use of a typical classifier which finds the closest class still leaves open the question of whether the test target truly belongs to that class. To decide whether a test target matches a stored target, common

Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition, 1988

A moving rigid object produces a moving image on the retina of an observer. It is shown that only... more A moving rigid object produces a moving image on the retina of an observer. It is shown that only the first-order spatial derivatives of image motion are sufficient to determine (i) the maximum and minimum time-to-collision of the observer and the object and (ii) the maximum and minimum angular velocity of the object along the direction of view. The second or higher order derivatives whose estimation is expensive and unreliable are not necessary. (The second-order derivatives are necessary to determine the actual motion of the object.) These results are interpreted in the image domain in terms of three differentiul invuriants of the image flow field: divergence, curl, and shear magnitude. In the world domain. the above results are interpreted in terms of the motion and local surface orientation of the object. In particular, the result that the minimum time-to-collision could be determined from only the first-order derivatives has a fundamental significance to both biological and machine vision systems. It implies that an organism (or a robot) can quickly respond to avoid collision with a moving object from only coarse information. This capability exists irrespective of the shape or motion of the object. The only restriction is that motion should be rigid.

AIAA Guidance, Navigation and Control Conference and Exhibit, 2007

2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems, 2007

proposed an approach for capturing a human similarity measure within a classifier, e.g., an artif... more proposed an approach for capturing a human similarity measure within a classifier, e.g., an artificial neural network, for face recognition. This is done by automatically generating and labeling arbitrarily large sets of morphed images (typically tens of thousands) in agreement with a human critic. One set is composed of images with reduced resemblance to the imaged person, yet recognizable by humans as that person (positive exemplars); the second set consists of images with some resemblance to the imaged person, but not enough to be recognizable as that person (negative exemplars). For each person of interest, a dedicated classifier is developed. From a practical point of view, it appears that the most challenging aspect of that approach is to completely enclose the decision region belonging to the person of interest. Because of the high dimensionality of the huamn face space, this is not simple matter especially for certain subjects. In this paper, we propose a new operator that morphs the image of the target person away from those of others. The new operator when applied together with the previous operator (morphing toward) helps to close the constructed decision region. Also, in this paper we propose the utilization of two networks for each target person; the added network covers not just the eyes and nose, but practically the entire face though in a coarse fashion. The second network, FaceNet, screens images before they are presented to the first network, EyeNet. The new developments have reduced the false accept rate by orders of magnitude with minimal impact on false reject rate. It now appreas, more than before, that the following important and long desired goal is within reach: "The similarity measure used in a face recognition system should be designed so that humans' ability to perform face recognition and recall are imitated as closely as possible by the machine [5]".

Computer Vision, Graphics, and Image Processing, 1990

It is a simple problem to fit one line to a collection of points in the plane. But when the probl... more It is a simple problem to fit one line to a collection of points in the plane. But when the problem is generalized to two or more lines then the problem complexity becomes exponential in the number of points because we must decide on a partitioning of the points among the lines they are to fit. The same is true for fitting lines to points in three-dimensional space or hyperplanes to data points of high dimensions. We show that this problem despite its exponential complexity can be formulated as an optimization problem for which very good, but not necessarily optimal, solutions can be found by using an artificial neural network. Furthermore, we show that given a tolerance one can determine the number of lines (or planes) that should be fitted to a given point configuration. This problem is prototypical of a class of problems in computer vision, pattern recognition, and data fitting. For example, the method we propose can be used in reconstructing a planar world from range data or in recognizing point patterns in an image.

Lecture Notes in Computer Science, 2004

Current appearance-based face recognition system encounters the difficulty to recognize faces wit... more Current appearance-based face recognition system encounters the difficulty to recognize faces with appearance variations, while only a small number of training images are available. We present a scheme based on the analysis by synthesis framework. A 3D generic face model is aligned onto a given frontal face image. A number of synthetic face images are generated with appearance variations from the aligned 3D face model. These synthesized images are used to construct an affine subspace for each subject. Training and test images for each subject are represented in the same way in such a subspace. Face recognition is achieved by minimizing the distance between the subspace of a test subject and that of each subject in the database. Only a single face image of each subject is available for training in our experiments. Preliminary experimental results are promising.

Biometric Technology for Human Identification VII, 2010

We report the development of a face recognition system which operates in the same way as humans i... more We report the development of a face recognition system which operates in the same way as humans in that it is capable of recognizing a number of people, while rejecting everybody else as strangers. While humans do it routinely, a particularly challenging aspect of the problem ...

Applications and Science of Artificial Neural Networks, 1995

ABSTRACT

Advanced Sciences and Technologies for Security Applications, 2006

Page 1. 14 The Use of Synthetic Data in Eye/Face Recognition Behrooz Kamgar-Parsi,1 Behzad Kamgar... more Page 1. 14 The Use of Synthetic Data in Eye/Face Recognition Behrooz Kamgar-Parsi,1 Behzad Kamgar-Parsi,2 and Benjamin N. Waber1,3 1Information Technology Division, Naval Research Laboratory, Washington, DC 20375 ...

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

Existing algorithms for finding the best match between two sets of 3D lines are not completely sa... more Existing algorithms for finding the best match between two sets of 3D lines are not completely satisfactory in the sense that they either yield approximate solutions, or are iterative which means they may not converge to the globally optimal solution. An even more serious shortcoming of the existing algorithms is that they are all non-invariant with respect to the translation

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 1999

The problem of screening images of the skies to determine whether they contain aircraft or not is... more The problem of screening images of the skies to determine whether they contain aircraft or not is both of theoretical and practical interest. After the most prominent visual signal in the infrared image of the sky is extracted, the question is whether the signal is a correct match of an aircraft. Common approaches calculate the degree of similarity of the

2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, 2006

required to rank face/facial images (as a precursor to recognition). Upon encounter, they recogni... more required to rank face/facial images (as a precursor to recognition). Upon encounter, they recognize the face or reject it as We propose an approach for capturing a human similarity unaila or pehp'sntbigtepro en ogt measure (within an artificial neural network, SVM, or other classifiers) for face recognition. That is, the following impor-

Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), 1999

Image understanding often involves object recognition, where a basic question is how to decide wh... more Image understanding often involves object recognition, where a basic question is how to decide whether a match is correct. Typically the best match (among a set of prestored objects) is assumed to be the correct match. This may work well in controlled environments (closed world). But, in uncontrolled environments (open world), the test object may not belong to the prestored

Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

Methods for matching sets of 3D lines depend on whether line lengths are finite or infinite. In t... more Methods for matching sets of 3D lines depend on whether line lengths are finite or infinite. In terms of line lengths, three basic cases arise in matching sets of lines: (1) finite to finite, (2) finite to infinite, and (3) infinite to infinite. For cases 1 and 2, which have not been treated in the literature, we present convergent iterative

Unmanned Ground Vehicle Technology, 1999

ABSTRACT

CVPR 2011, 2011

We revisit the problem of matching a set of lines in the 2D image to a set of corresponding lines... more We revisit the problem of matching a set of lines in the 2D image to a set of corresponding lines in the 3D model for the following reasons. (a) Existing algorithms that treat lines as innitely long contain a aw, namely, the solutions found are not invariant with respect to the choice of the coordinate frame. The source of this

Proceedings of International Conference on Image Processing, 1997

ABSTRACT

Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001

Object extraction from an IR image background is of great interest both to the military and the c... more Object extraction from an IR image background is of great interest both to the military and the commercial sector. A convenient and popular approach to object extraction is image thresholding. In this paper, we describe a new and easy to implement approach for extracting object(s) in single frame IR images, which has many similarities to image thresholding. Both on the basis of theoretical considerations and experimental results, however, our approach appears to be noticeably more dependable than image thresholding for IR images