The FERET Evaluation Methodology for Face-Recognition Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
A Qualitative Approach to Classifying Head and Eye Pose
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Face recognition: A literature survey
ACM Computing Surveys (CSUR)
Neurons Tune to the Earliest Spikes Through STDP
Neural Computation
Using Biologically Inspired Features for Face Processing
International Journal of Computer Vision
Neural network-based head pose estimation and multi-view fusion
CLEAR'06 Proceedings of the 1st international evaluation conference on Classification of events, activities and relationships
Detection of head pose and gaze direction for human-computer interaction
PIT'06 Proceedings of the 2006 international tutorial and research conference on Perception and Interactive Technologies
Hi-index | 0.00 |
We present a biologically inspired model for learning prototypical representations of head poses. The model employs populations of integrate-and-fire neurons and operates in the temporal domain. Times-to-first spike (latencies) are used to develop a rank-order code, which is invariant to global contrast and brightness changes. Our model consists of 3 layers. In the first layer, populations of Gabor filters are used to extract feature maps from the input image. Filter activities are converted into spike latencies to determine their temporal spike order. In layer 2, intermediate level neurons respond selectively to feature combinations that are statistically significant in the presented image dataset. Synaptic connectivity between layer 1 and 2 is adapted by a mechanism of spike-timing dependent plasticity (STDP). This mechanism realises an unsupervised Hebbian learning scheme that modifies synaptic weights according to their timing between pre- and postsynaptic spike. The third layer employs a radial basis function (RBF) classifier to evaluate neural responses from layer 2. Our results show quantitatively that the network performs well in discriminating between 9 different input poses gathered from 200 subjects.