CMSC828B Advanced Topics in Information Processing: Recent Advances in Biometrics

Announcements

Description

In biometrics we study methods for identifying organisms (usually people) from measurements of their characteristics.  In this class we will read recent papers in order to understand the state of the art in biometrics.  Topics considered will be based on student interest, but I expect to have a significant emphasis on face recognition, with a broad range of additional topics.  This course is intended primarily for students with a research interest in biometrics or computer vision, and will not be a core MS or PhD class for CS students.

Possible class topics include:

• Face Recognition:

  • Lighting Variation

  • Aging

  • Pose Variation

  • Expression Variation

  • 3D information

  • Linear subspace methods

  • Learning-based methods

  • Using morphable-3D models and 2D images

  • Using web images.  Check, for example, the LFW web page for paper ideas.

  • Visual psychology.

  • Recent papers of interest.  Suggested work includes:

    • Sparse representations for face recognition.  See work, eg., by Ma, Sastry, Yang, Wright....

    • Partial Least Squares.  Schwartz, Guo and Davis

    • Attributes for face recognition.  See work from Belhumeur's group.

• Fingerprints

• Palm Prints

• Ears

• Iris

• Non-human biometrics

  • of individuals (eg., recognizing individual salamanders, or whales)

  • of species (eg., identifying plant species).

• DNA - Identification of individuals from DNA and/or DNA barcoding for species identification.

• Gait

• Speaker identification

• Multi-biometrics (information fusion)

• Secure biometrics

• Skeletons/Teeth

• Signatures

Requirements

Here is my current plan for the workload of the class. 

1) Reports.  Prior to class, students will read assigned papers and write a one page report summarizing and critiquing the work. Each student must turn in 14 reports.  Students should not write a report for classes for which they are giving a presentation.

2) Presentation.  Each student will take responsibility for presenting work during one class.  This will include selecting two papers to be read by the class, and presenting this work and related work to the class.  Students currently performing research in biometrics are encouraged to give a presentation about their research. In this case, the student should select two papers by other authors that provide appropriate background to this research.  For detailed expectations of presentation, see this rubric.

3) Project.  Students will implement and experiment with biometric methods, using real-world data sets. 

4) Class Participation.  Everyone should read papers before class and contribute to discussion of them.

Note: visitors or auditors are welcome.  However, if you are attending a class in which we will discuss papers, you should complete a report on one of these papers (see requirement 1).

Class Schedule

Student Honor Code

The University of Maryland, College Park has a nationally recognized Code of Academic Integrity, administered by the Student Honor Council. This Code sets standards for academic integrity at Maryland for all undergraduate and graduate students. As a student you are responsible for upholding these standards for this course. It is very important for you to be aware of the consequences of cheating, fabrication, facilitation, and plagiarism. For more information on the Code of Academic Integrity or the Student Honor Council, please visit http://www.shc.umd.edu. To further exhibit your commitment to academic integrity, remember to sign the Honor Pledge on all examinations and assignments: "I pledge on my honor that I have not given or received any unauthorized assistance on this examination (assignment)."