Background
Note: I have recently finished my postdoc at LBL and am now at Google, Inc.
From 2005 to 2007 I was a postdoctoral researcher in the Visualization Group at Lawrence Berkeley National Laboratory, where I applied statistical learning algorithms to the analysis of scientific data. Projects included recognizing supernovae from photometric and geometric futures using Support Vector Machines, classifying time-varying spectra from observed and synthetic supernovae via component analyses, and finding statistical dependencies between hurricane occurrences and spatiotemporal variables in climate simulations.
I spent a year as postdoctoral researcher in the Imaging and Informatics Group applying vision and learning methods to miscroscopy imagery used by radiation biologists as a way to quantify the presence in cell nuclei of proteins crucial to DNA repair.
I earned my Ph.D. in EECS from MIT in May 2002 in the Computer Vision Group at the Artificial Intelligence Laboratory, now CSAIL.
Current Projects
  • Recognition of Supernovae using Support Vector Machines

  • Classification of Supernova Spectra via Non-negative Matrix Factorization

  • Modeling Protein Expression Features from Fluorescence Microscopy using Independent Component Analysis

    Past Projects

  • Projective Minimal Analysis of Camera Geometry

  • Activity Monitoring from Multiple Views

  • Real-Time Face Verification

    		•
    Talks
  • Supernova Recognition Using Support Vector Machines, Neyman Seminar, Department of Statistics, UC Berkeley, September 20, 2006

  • Finding Features and Anomalies in Scientific Data, Tapia Diversity in Computing Conference, October 22, 2005

  • Statistical Analysis of Subcellular Proteins in Microscopy Imagery, Bay Area Scientific Computing Day, March 5, 2005

  • Projective Geometry for Computer Vision, LBL Scientific Computing Seminar, May 12, 2004

    • Publications
  • Supernova Recognition using Support Vector Machines., R. Romano, C. Aragon, and Chris Ding. Proceedings of the 5th International Conference of Machine Learning Applications. December 14-16, 2006. Best Application Paper Award

  • Projective Minimal Analysis of Camera Geometry. Raquel A. Romano. Ph.D. Thesis. May 2002. (ps.gz)

  • Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame. L. Lee, R. Romano, and G. Stein. IEEE Transactions on Pattern Recognition and Machine Intelligence, Special Section on Video Surveillance and Monitoring. Vol. 22, No. 8, August 2000.

  • Using Adaptive Tracking to Classify and Monitor Activities in a Site. W.E.L. Grimson, L. Lee, R. Romano, and C. Stauffer. Proceedings of Computer Vision and Pattern Recognition (CVPR), 1998, pp.22-31. ps.gz)

  • Face Verification for Real-time Applications. R. Romano, D. Beymer, and T. Poggio. Proceedings of Image Understanding Workshop. Vol. 1, Palm Springs, CA, February 1996, pp. 747-756. (ps.gz)

    		•
    Links
  • LBL Visualization Group

  • LBL Imaging and Informatics Group

  • MIT Artificial Intelligence Laboratory Vision Group

  • INRIA Robotvis Group (now Odyssee)

    • Outreach
  • Education 198: Strategies for Sucess at Cal for Science, Engineering and Mathematics Transfer Students, UC Berkeley, Spring 2005

  • Puente Program

  • LBL Latino and Native American Association

    		•
    romano@hpcrd.lbl.gov