Gait Recognition Using Subspace Clustering
|Betreuer||Maryam Babaee, M.Sc.
Tel.: +49 (0)89 289-28543
|Beschreibung||Personal identification based on the gait cues includes detection methods based on the biometric characteristics of gait. Generally speaking, a variety of biometric features for recognizing persons can be used such as face, iris, fingerprint, etc. In this project, the Gait (the way of walking) is investigated as a biometric recognition feature. The main advantage of gait as a biometric feature compared to physiological features is the ability to recognize people from greater distance .
Cluster analysis seeks to discover groups (clusters) of similar objects. The objects are usually feed into a classifier as a vector of measurements, or a high dimensional feature vector. In high dimensional space, many dimensions are irrelevant and the data becomes sparse. In such cases, Subspace Clustering methods can be applied to search for meaningful low dimensional representations. By identifying the different subspaces which exist in the original high dimensional space, we can find which of different attributes are related. In other words, these algorithms attempt to identify clusters embedded in a subspace of high dimensional data.
In this project, we aim to develop a novel Subspace Clustering approach which is specific for Gait data to capture meaningful and compact representation of Gait data and ultimately recognize different individuals based on their Gait.
|Voraussetzung||Programming skill in C++ and Matlab is highly required. Additionally, solid background in machine learning and pattern recognition is desirable. In case you have any questions, please write me an 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.|