Face Recognition for Cognitive Robots

Face Recognition for Cognitive Robots

Gaisser, F.

Jonker, P.P. (mentor)
Rudinac, M. (mentor)

Mechanical, Maritime and Materials Engineering

BioMechanical Engineering

BMD

2013-01-29

In the near future the elderly population will increase in size up to a point that there are not enough people to provide support. One solution would be developing service robots, that can perform household tasks and in that way allow elderly to live longer independently. These service robots have to be able to adapt to changing environments, which requires a flexible framework that can recognize and learn objects regardless of the environment or the robot architecture. In this thesis such a framework, consisting of localization, description, classification and learning modules structured as a pipeline is introduced. Various types of objects require different methods to be used in each of the modules. For efficient memory usage these methods are dynamically loaded into the pipeline in the introduced framework. For human-robot interaction users have to be robustly identified and learned online. Exist-ing state of the art methods for face recognition, such as K-Nearest Neighbours (KNN) and Principal Component Analysis (PCA), do not support online learning of faces and lack the recognition performance required to be used in real-world situations. Hence the Class Average Principal Component Analysis (CAPCA) method is developed in this thesis as a descriptor. This method provides the required performance by increasing the separability of the classes by maximizing the inter-class and minimizing intra-class variations. The speed is increased significantly by selecting only the most representative samples. Additionally to allow for classification of unknown faces, the novel Certainty K-Nearest Neighbours (CertKNN) method has been introduced. The main benefit over the state of the art methods is finding the relation between the distance of classification and the certainty of that classification. This relation is automatically calculated from the data belonging to each class. In that way nearly optimal unknown classification can be done. Finally to further improve recognition performance a method has been developed that utilizes multiple frames in classification. To prove the benefits of the introduced methods extensive experiments have been performed on a state of the art face recognition database. The best performance was achieved with a F-measure of 96% and 90% for respectively known and unknown classification. Training speed was increased up to 100 times, which allows for online learning of faces. Lastly the introduced methods were applied on the Delft Robotics service robot and extensively tested in the RoboCup@Home challenge.

face recognition
cognitive robots
robotics

http://resolver.tudelft.nl/uuid:4b912a2c-2951-411f-be76-7ef2cf135703

2014-01-29

Student theses

master thesis

(c) 2013 Gaisser, F.