Thema
Gait Recognition by Manifold Learning
Typ Master, Forschungspraxis
Betreuer Maryam Babaee, M.Sc.
Tel.: +49 (0)89 289-28543
E-Mail: maryam.babaee@tum.de
Sachgebiet Computer Vision
Beschreibung As one of the biometric features for human recognition, Gait (the way of walking) [1] has drawn attention in recent years, since it is able to recognize people from large distance in spite of other biometric features such as face, fingerprint, iris. In gait recognition, a sequence of images showing a person walking are analyzed as input data. To interpret such high dimensional data effectively, it is required to eliminate redundant or irrelevant feature data by utilizing dimensionality reduction methods such as manifold learning techniques (e.g., Laplacian Eigenmap). In manifold learning, it is assumed that a low-dimensional non-linear manifold [2] is embedded in a high-dimensional space and the techniques in this area seek to extract this embedded manifold [3]. The result of applying a manifold learning method on a synthetic 3D data sample is shown below.


The student in this project will work on analyzing the gait data by applying different manifold learning techniques in order to get a distinguishing representation of a gait sequence data.
Refs:
[1] marathon.csee.usf.edu/GaitBaseline/
[2] en.wikipedia.org/wiki/Manifold
[3] en.wikipedia.org/wiki/Nonlinear_dimensionality_reduction
Voraussetzung The student is expected to have good knowledge in pattern recognition field as well as Matlab/ C++ programming skills. For further discussion, please first contact me via email.
Bewerbung If you are interested in this topic, we welcome the applications via the email address above. Please set the email subject to “<Type of application> application for topic 'XYZ'”, ex. “Master’s thesis application for topic 'XYZ'”, while clearly specifying why are you interested in the topic in the text of the message. Also make sure to attach your most recent CV (if you have one) and grade report.