CMU

.
Ahmed Bilal Ashraf
PhD Candidate
Department of ECE

Email address: bilal@cmu.edu
Office:Newell Simon Hall, NSH-4222
Phone: (412) 268-3132

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

 

Research Interests

My research interests include Artificial Intelligence, Machine Learning, Robotics and Computer Vision. My long term research aspiration is to let machines gain faculties and adroitness that put them at par with humans in terms of performing tasks in which humans currently outperfom the machines. More specifically I am interested in the applications of machine learning to spatio-temporal image analysis, object tracking and alignment, face analysis , face identification, verification, and expression recognition. I am advised by Prof. Simon Lucey. I am a member of the Advanced Multimedia Processing Lab (now at Cornell)

Jump to: Research / Selected Projects | Publications | Talks | Teaching | Resume' |


Research / Selected Projects

 

SVM Rotation Margin Manipulation in Support Vector Machines
SVM Rotation
SVM Rotation
SVM Rotation

A. B. Ashraf , S. Lucey and Tsuhan Chen,. Re-interpreting the application of Gabor filters as a manipulation of the margin in linear support vector machines. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), (accepted), 2010

 

[PDF].



 

SVM Rotation Fast Image Alignment in the Fourier Domain

In our recent work we have shown that the conventional Lucas-Kanade algorithm can equivalently be cast in the Fourier domain, instead of the conventional spatial domain. With this formulation, we have shown that performing alignment in the high dimensional feature spaces derived from a bank of filters becomes mathematically equivalent to performing alignment in the low dimensional image space, if appropriate weightings are applied in the Fourier domain. This technique renders the Fourier-LK algorithm robust to noisy artifacts like illumination in comparison to the conventional Lucas-Kanade algorihtm.

A. B. Ashraf , S. Lucey and Tsuhan Chen,. Fast Image Alignment in the Fourier Domain . IEEE Conference on Computer Vision and Pattern Recognition), 2010 (CVPR) (accepted),

[PDF]

See Fourier-Alignment Demo..


 

Learning Patch-Correspondence for Viewpoint Invariance
 

A. B. Ashraf , S. Lucey and Tsuhan Chen,. Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition . IEEE Conference on Computer Vision and Pattern Recognition), Anchorage, Alaska, 2008 (CVPR), (Oral)

[PDF]

See Patch Correspondence Demo..


 

Pain Expression Recognition
 

A. B. Ashraf, S. Lucey, J. F. Cohn, T. Chen, K. M. Prkachin, and P. E. Solomon. The painful face II-- Pain expression recognition using active appearance models. International Journal of Image and Vision Computing, 27(12):1788-1796, November 2009., [PDF]

A. B. Ashraf, S. Lucey, J. F. Cohn, T. Chen, K. M. Prkachin, and P. E. Solomon. The painful face -- Pain expression recognition using active appearance models. ACM International Conference on Multimodal Interfaces, Nagoya, Japan 2007. (Oral)., [PDF]

See Pain Detection Demo.


 

Spontaneous Facial Action Recognition
 

Simon Lucey, Ahmed Bilal Ashraf, and Jeffrey Cohn. Investigating Spontaneous Facial Action Recognition through AAM Representations of the Face. In K. Kurihara, editor, Face Recognition Book. Pro Literatur Verlag, Mammendorf, Germany, April 2007

 

[PDF].


 

Occupant Classification for Air-bag Deployment

 

Air bags are deployed upon frontal impact to provide a cushion between the occupant and the vehicle. But in case the passenger side seat is occupied by an infant especially seated in a Rear Facing Infant seat, the deployed air-bag strikes the infant’s neck with such immense an impact that crosses the child’s impact resistance and the child dies. There was therefore a need to develop an intelligent system that detects the type of the occupant and adaptively changes the deployment parameters. The vision based solution employs a camera installed in the vehicle that captures the image of the passenger side seat and hands it over to the classification system.

M. R. Hamid,, A. Baloch , A. B. Ashraf , N. A. Zaffar,,. Object Segmentation Using Feature-based Conditional Morphology . IEEE Conference on Image Analysis and Processing, Italy (2003)

 

[PDF].


 

Publications | [Home]
 

A. B. Ashraf , S. Lucey and Tsuhan Chen,. "Re-interpreting the application of Gabor filters as a manipulation of the margin in linear support vector machines". IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI),, 2010 [PDF].

 
 
 

A. B. Ashraf , S. Lucey and Tsuhan Chen,. Fast Image Alignment in the Fourier Domain . IEEE Conference on Computer Vision and Pattern Recognition), 2010 (CVPR) (accepted), [PDF]

 
 
 

A. B. Ashraf , S. Lucey and Tsuhan Chen,. Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition . IEEE Conference on Computer Vision and Pattern Recognition), Anchorage, Alaska, 2008 (CVPR), (Oral) [PDF]

 
 
 

A. B. Ashraf, S. Lucey, J. F. Cohn, T. Chen, K. M. Prkachin, and P. E. Solomon. The painful face II-- Pain expression recognition using active appearance models. International Journal of Image and Vision Computing, 27(12):1788-1796, November 2009., [PDF]

 
 
 

A. B. Ashraf, S. Lucey, J. F. Cohn, T. Chen, K. M. Prkachin, and P. E. Solomon. The painful face -- Pain expression recognition using active appearance models. ACM International Conference on Multimodal Interfaces, Nagoya, Japan 2007. (Oral)., [PDF]

 
 
 

Simon Lucey, A. B. Ashraf, and Jeffrey Cohn. Investigating Spontaneous Facial Action Recognition through AAM Representations of the Face. In K. Kurihara, editor, Face Recognition Book. Pro Literatur Verlag, Mammendorf, Germany, April 2007 [PDF]

 
 
 

M. R. Hamid,, A. Baloch , A. B. Ashraf , N. A. Zaffar,,. Object Segmentation Using Feature-based Conditional Morphology . IEEE Conference on Image Analysis and Processing, Italy (2003) [PDF].

 

 

Talks | [Home]

-Featureless Computer Vision,. Robotics Institute, Carnegie Mellon University, September 4, 2009 [Talk].

-Learning Patch Correspondences for Improved Viewpoint Invariant Face Recognition . CVPR Oral Talk, Anchorage, Alaska, June 26, 2009 [Talk]

-Pose-Invariant Recognition Using Single Gallery Image, Department of ECE, Carnegie Mellon University, November 12, 2008 [Talk]

-Video Content Analysis, Department of ECE, University of Maryland, College Park, October 2008 [Talk]

-The Painful Face, . ACM ICMI Oral Talk, Nagoya, Japan, November 2007 [Talk]


 

Teaching | [Home]

-Fall 2008: Signals and Systems

-Spring 2009: Signals and Systems


 

Resume' | [Home]

[Download Resume']


 

Disclaimer

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.