Javascript must be enabled for the correct page display

Machine Learning for 3D Face Recognition using off-the-shelf sensors

Schimbinschi, F. (2013) Machine Learning for 3D Face Recognition using off-the-shelf sensors. Master's Thesis / Essay, Artificial Intelligence.

[img]
Preview
Text
AI-MAI-2013-F.Schimbinschi.pdf - Published Version

Download (2MB) | Preview
[img] Text
SchimbinschiAkkoordWiering.pdf - Other
Restricted to Repository staff only

Download (43kB)

Abstract

The human brain is inherently hardwired to read psychological state before identity, hence its robustness towards the dynamic nature of faces and viewpoint changes. The novelty of this research consists in learning abstract atomical representations of shape cues, thus having the potential to solve multiple classification problems since a depiction unit can have multiple task-specific attributes. Machine learning versatility is paramount and as such multiple ensembles of varying complexity are trained based on unsupervised specialization of experts. A dataset of 18 individuals was recorded based on different variances in pose, expression and distance to the Kinect sensor. Using 3D object feature descriptors, the performance for face recognition is studied over 36 variance-specific pair tests, concluding that simple ensembles outperform complex ones, since the utility of each expert is highly dependent on the sampling resolution, distance metric and type of features. The methodology is robust towards occlusions and the performance can reach accuracies up to 90% depending on the complexity of the dataset, despite that there is no human supervision for generating the face region labels.

Item Type: Thesis (Master's Thesis / Essay)
Supervisor:
Supervisor nameSupervisor E mail
Wiering, M.UNSPECIFIED
Schomaker, L.UNSPECIFIED
Degree programme: Artificial Intelligence
Thesis type: Master's Thesis / Essay
Language: English
Date Deposited: 15 Feb 2018 07:55
Last Modified: 02 May 2019 09:36
URI: http://fse.studenttheses.ub.rug.nl/id/eprint/11370

Actions (login required)

View Item View Item