Advanced Multimedia Processing Lab -- Group Member -- Wende Zhang

            About AMP Lab        Projects        Downloads        Publications        People        Links

Group Member

Wende Zhang
PhD. Student

Personal Homepage:

Office: Porter Hall B32
Lab: Porter Hall B6
Phone: 412-268-7100
Fax: 412-268-3890
Mailing Address:
Department of ECE, Carnegie Mellon University,
5000 Forbes Avenue, Pittsburgh,
PA 15213-3890

[Research Interests]        [Project]      [Publications

Research Interests

Research Focus:

We introduce a "Boids" concept to model the intelligent vehicles.  Each intelligent vehicle follows simple rules/operations and communicates locally with the neighbor vehicles for traffic-aware route planning.

Design the key generation algorithms based on biometrics. The focus of the research is: stability and security of  the key for the target user.

Design the classification algorithms for personal authentication.

Fuse multi-biometric features of the same person from different biometric sensors for personal authentication. 

Build the system for capturing  multi-biometric data, like face, fingerprint, iris and voiceprint, etc.

  Top of this page



Information Sharing for Dynamic Route Planning

In this project, we assume that some vehicles can share information among them locally, while the others can not. Based on the shared information, each vehicle will analyze the local traffic condition in real time, and build up the dynamic map, which contains real-time traffic information for route planning by the simple operations to minimize the traveling time.

Please refer to the Information sharing for dynamic route planning project page for more details. 


Algorithms and Security Analysis for Key Generation based on Biometrics 

We build a key generation system based on biometrics. The system first extract the biometric features from the biometric data. Then the features are compared with thresholds to the generate bio-key. We also analyze the security problem of user information associated key generation (UIAKG) systems. We consider three kinds of attacks from the hacker: the exhaustive search attack, the authentic key statistics attack and the device key statistics attack.

Please refer to the Key generation based on biometrics project page for more details. 



Algorithms for Personal Authentication

We introduce a new classification algorithm based on the concept of Symmetric Maximized Minimal distance in Subspace (SMMS). SMMS tries to identify a subspace in which all the authentic samples are clustered together and all the imposter samples are far away from the authentic samples.  The optimality of the subspace is determined by maximizing the minimal distance between the authentic samples and the imposter samples in the subspace.  Using face authentication as an example, we show that the proposed algorithm outperforms the linear classifier based on support-vector machines (SVM).  

For more details on the project please see the Personal authentication based on SMMS project page.


Sensor Fusion

 The Distinguish Component Analysis+ weighting method is proposed to improve the performance of face verification. The same method is also proposed to perform sensor fusion. This algorithm will outperform the single decision.

For more details on the project please see the Sensor fusion project page.


Multi-biometric Data Acquisition Station (MBDAS)

In order to evaluate the proposed biometric authentication / identification algorithms, acquire multiple biometrics from an individual at the same time and test what biometric sensors and sensor resolutions/sizes are reasonable candidates, the MBDAS system is built. 

For more details on the project please see the Sensor fusion project page.


Top of this page



Conference Papers: 


Research Report: 


Top of this page

This website is maintained by Devi Parikh
Copyright © 2001 
Advanced Multimedia Processing Lab. All rights reserved.
Revised: January 20, 2008 .