New method for vanishing point detection
CVGIP: Image Understanding
Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Geometric computation for machine vision
Geometric computation for machine vision
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Using Generative Models for Handwritten Digit Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Approaches to Feature-Based Object Recognition
International Journal of Computer Vision
Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Graph Matching With a Dual-Step EM Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Thermal Imaging for Anxiety Detection
CVBVS '00 Proceedings of the IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications (CVBVS 2000)
A Comparative Analysis of Face Recognition Performance with Visible and Thermal Infrared Imagery
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Face Identification across Different Poses and Illuminations with a 3D Morphable Model
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Physiology-Based Face Recognition in the Thermal Infrared Spectrum
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, a new method is proposed to register visible and infra-red face images. The vanishing-point based approach [9] is applied to the visible image to determine the 3D pose of the human head. Then the corresponding pose with respect to the infra-red camera is computed through the known relationship by calibration between the visible and infra-red cameras. By doing so, the skin temperature range within the infra-red image can be superimposed over the visible face image. We use the EM strategy to first compute the 3D pose using some initially learned (PCA) model parameters, then update iteratively the parameters for individual persons and their facial expressions till convergence. The EM technique models data uncertainty using Gaussian mixtures defined over positions and orientation of facial plane. The resulting weighted parameters estimation problem is solved using the Levenberg-Marquardt method. The results on the synthetic data and real images have verified the performance of the approach.