Sadjad Asghari Esfeden

Research

  • Synergetic Media Learning (SMILE) Laboratory
    Department of ECE, Northeastern University, Boston, MA, USA
    Research Assistant - Supervisor: Dr. Yun Fu, Sep. 2013 - Dec. 2014

    • Emotion Detection
      We detect emotions from EEG signals and facial expressions in response to videos. Using power spectral features from EEG signals and facial landmarks, we detect valence (pleasantness) levels for each frame continuously. We also study the effect of the changes in the stimulus (audio and visual features) on the emotional response of viewers.

  • Hoyos Labs.
    Cambridge Innovation Center, Cambridge, MA, USA
    Research and Development Intern - Computer Vision Group, Summer 2014

    • Face Liveness Detection (Biometrics)
      We designed and developed several real-time tests to determine face liveness using smart phones’ front camera (developed for iOS and Android). Using Image processing and computer vision methods (facial landmark detection, frequency and dynamic texture analysis, motion detection, 3D face model, etc.) we could differentiate between still images and videos and real faces for authentication.

  • Computational Models of Visual Cortex (CMVC) Group
    BMI and Neuroscience Laboratories, School of Cognitive Sciences (SCS), Institute for Research in Fundamental Sciences (IPM), Tehran, Iran
    Training and Research Assistant - Supervisor: Dr. Reza Ebrahimpour, Jun. 2012 – Aug. 2013

    • Biologically Inspired Universal Dictionary of Visual Features for Object Recognition
      We attempted to find a dictionary of visual features and use it in several tasks of object recognition and categorization. This universal dictionary is based on recent biological evidence of human visual system.

  • Social Networks Laboratory
    School of ECE, University of Tehran, Tehran, Iran
    Training and Research Assistant - Supervisor: Dr. Masoud Asadpour

    • Mining Social Network of Persian Blogosphere, Sep. 2011 – Jan. 2012
      We studied blogs of Blogfa and their web graph, and analyzed the websites that cited by these blogs. Based on this study we suggested a method to estimate the content similarity among these websites.

Feel free to contact me about any of these projects.