June 26, 2011
June 26, 2011
June 29, 2011
22.245.1 - 22.245.9
Assessing the Impact of a Biometrics Course on Students’ Digital Signal Processing KnowledgeAbstractThe ability of investigators to analyze sound, image, and video data and to efficiently searchthrough large databases of biometric data such as fingerprints or facial images has revolutionizedthe field of forensics over the last couple of decades. While biometric technology is increasinglyimportant in forensics and security applications and is currently a very active research area, thistopic has predominantly been addressed at the graduate level due to the mathematicalbackground required for research in the area. We have designed a course in Biometric SignalProcessing Course which allows undergraduate students in Electrical and Computer Engineering(ECE) to explore these important technologies.An important aspect of our NSF project and the design of the course, which consists of lecturesand hands-on laboratories with biometric sensors, was to give students a second opportunity tomore fully grasp the fundamentals of Digital Signal Processing. Consequently, students areintroduced to Biometrics with a speaker recognition system which ties nicely into the one-dimensional signal processing theory that they have already learned. Students first enhance thespeech to produce a signal which can be used for recognition and this provides students anopportunity to refresh their knowledge of filtering and sampling. Linear Predictive Coding(adaptive filtering) and Dynamic Time Warping (DTW), which is used to compensate fordifferent speaker rates, are then used in a speaker recognition system which students are taskedto complete on their own. In the second part of the course, the students work with imageprocessing methods in designing a face recognition system and working with a fingerprintrecognition system. This naturally leads us to cover the fundamentals of image processing inlectures and laboratories to allow students to understand how images can be manipulated tofacilitate recognition. In particular, topics such as sampling, filtering, and frequency analysis intwo dimensions are covered.We believe that the application of signal processing methods to these important and funtechnologies will motivate students and greatly increase their understanding of signal processingprinciples such as sampling, filtering, interpolation, and frequency domain representation. Weare using the Discrete Time Signals and Systems Concept Inventory (DT-SSCI) exam before andafter the course as an objective assessment tool. In the past, DT-SSCI has been used to assessstudent learning in introductory courses, so our project represents a novel application of this toolas students have already been exposed to the material in a previous course. We will determinethe successes and failures of the course using the results from the DT-SSCI and be able to use theresults to strengthen future offerings and adapt the material to better address students’ problemareas. Furthermore, we will conduct focus group interviews at the end of the term to determinestudents’ confidence in their knowledge of core signal processing concepts and which aspects ofthe course (perhaps pinpointing particular exercises, laboratories, or projects) had the mostimpact in enhancing their understanding of signal processing methods. The results of theseanalyses will be completed in mid-November and will be fully documented in the final submittedpaper.
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2011 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015