Search For:

Displaying 1-10 out of 10 total
SCiFI - A System for Secure Face Identification
Found in: Security and Privacy, IEEE Symposium on
By Margarita Osadchy, Benny Pinkas, Ayman Jarrous, Boaz Moskovich
Issue Date:May 2010
pp. 239-254
We introduce SCiFI, a system for Secure Computation of Face Identification. The system performs face identification which compares faces of subjects with a database of registered faces. The identification is done in a secure way which protects both the pri...
 
Loose shape model for discriminative learning of object categories
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Margarita Osadchy, Elran Morash
Issue Date:June 2008
pp. 1-6
We consider the problem of visual categorization with minimal supervision during training. We propose a partbased model that loosely captures structural information. We represent images as a collection of parts characterized by an appearance codeword from ...
 
Surface Dependent Representations for Illumination Insensitive Image Comparison
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Margarita Osadchy, David W. Jacobs, Michael Lindenbaum
Issue Date:January 2007
pp. 98-111
We consider the problem of matching images to tell whether they come from the same scene viewed under different lighting conditions. We show that the surface characteristics determine the type of image comparison method that should be used. Previous work h...
 
Incorporating the Boltzmann Prior in Object Detection Using SVM
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Margarita Osadchy, Daniel Keren
Issue Date:June 2006
pp. 2095-2101
In this paper we discuss object detection when only a small number of training examples are given. Specifically, we show how to incorporate a simple prior on the distribution of natural images into support vector machines. SVMs are known to be robust to ov...
 
On the Equivalence of Common Approaches to Lighting Insensitive Recognition
Found in: Computer Vision, IEEE International Conference on
By Margarita Osadchy, David W. Jacobs, Michael Lindenbaum
Issue Date:October 2005
pp. 1721-1726
Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighti...
 
Using Specularities for Recognition
Found in: Computer Vision, IEEE International Conference on
By Margarita Osadchy, David Jacobs, Ravi Ramamoorthi
Issue Date:October 2003
pp. 1512
Recognition systems have generally treated specular highlights as noise. We show how to use these highlights as a positive source of information that improves recognition of shiny objects. This also enables us to recognize very challenging shiny transparen...
 
Anti-Sequences: Event Detection by Frame Stacking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Margarita Osadchy, Daniel Keren, Yaniv Gal
Issue Date:December 2001
pp. 46
This paper presents a natural extension of the newly introduced
 
Antifaces: A Novel, Fast Method for Image Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Daniel Keren, Margarita Osadchy, Craig Gotsman
Issue Date:July 2001
pp. 747-761
<p><b>Abstract</b>—This paper offers a novel detection method, which works well even in the case of a complicated image collection—for instance, a frontal face under a large class of linear transformations. It is also successfully applied...
 
Image Detection Under Varying Illumination and Pose
Found in: Computer Vision, IEEE International Conference on
By Margarita Osadchy, Daniel Keren
Issue Date:July 2001
pp. 668
This paper focuses on the detection of objects with Lambertian surface under both varying illumination and pose. We offer to apply a novel detection method that proceeds by modeling the different illuminations from a small number of images in the training ...
 
POSTER: Secure authentication from facial attributeswith no privacy loss
Found in: Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security (CCS '13)
By Mahmood Sharif, Margarita Osadchy, Orr Dunkelman
Issue Date:November 2013
pp. 1403-1406
Biometric authentication is more secure than using regular passwords, as biometrics cannot be "forgotten" and contain high entropy. Thus, many constructions rely on biometric features for authentication, and use them as a source for "good" cryptographic ke...
     
 1