David W. Jacobs


Professor, Department of Computer Science and UMIACS,
at the University of Maryland.



Contact Info:

My office is in Room 4421, A.V. Williams Building.

Surface Mail: Department of Computer Science and UMIACS;
A.V. Williams Building; University of Maryland;
College Park, MD 20742
Phone: (301) 405-0679       Fax: (301) 314-9115
Email: djacobs at cs.umd.edu
Homepage: http://www.cs.umd.edu/~djacobs

Teaching

Spring 2013 – CMSC 828 Linear Subspaces and Manifolds in Computer Vision and Machine Learning

Fall 2012 - CMSC 426 Image Processing

Spring 2012 - CMSC 828 Image Segmentation

Fall 2011 - CMSC 131 Object-Oriented Programming I

Spring 2011 - CMSC 131 Object-Oriented Programming I

Fall 2010 - CMSC 828B Recent Advances in Biometrics

Spring 2010 - CMSC 426   Computer Vision (aka Image Processing)

Fall 2009 - CMSC 828 Image Segmentation

Spring 2009 - CMSC 828 Approaches to Representing and Recognizing Objects

Spring 2008 - CMSC 828 Seminar in Scene Analysis: Course Description, Schedule of Talks

Fall 2007 -- CMSC 427 Computer Graphics

Spring 2007 -- CMSC 427 Computer Graphics

Fall 2006 -- CMSC 828 Image Segmentation

Spring 2006 -- CMSC 828 Approaches to Representing and Recognizing Objects

Fall 2005 -- CMSC 426  Computer Vision

Spring 2004 -- CMSC 427 Computer Graphics

Fall 2004 -- CMSC 828 Image Segmentation

Spring 2004 -- CMSC 426 Computer Vision

Fall 2003 -- CMSC 828 Approaches to Representing and Recognizing Objects  

Spring 2003 -- CMSC 426Computer Vision

Research Interests

My research has spanned a range of topics in vision. My primary focus has been on the problem of how to recognize objects in images. This is a central problem in vision that I find particularly fascinating because it lies between concrete, lower-level vision problems and central cognitive systems that attempt to tie semantics to the world. It is also a critical problem in many applications in multimedia and robotics. I have also done quite a bit of work in the computational and psychological study of perceptual organization. This is the lower level problem of how to identify the surfaces of potential objects before recognizing them. I see perceptual organization as integral to the recognition process, and in part my work attempts to show how these two problems can be unified.

My recent work in recognition has mainly focused on understanding how to recognize objects under varying lighting conditions, varying poses, and how to match images of objects that may deform or otherwise vary non-rigidly.  I have also been interested in using techniques from computer vision in developing user interfaces and in graphics.  Our group is applying some of this work to build an electronic field guide for botanists, using object recognition methods to automatically match the leaves of plants.  That work is in collaboration with people at the Smithsonian Institution, and at Columbia University.  Our iphone app, Leafsnap, is now available.  My students and I have also applied our work in recognition to a number of face recognition systems.

Selected Publications

Curriculum Vitae (includes full list of publications)

Students

Current PhD Students:

Former PhD Students:

Code

Leafsnap