Component-Based Face Recognition with 3D Morphable Models

By Jennifer Huang, Bernd Heisele, Volker Blanz. 2004 Conference on Computer Vision and Pattern Recognition Workshop, 2003

482 citations recorded by the source corpus.

We present a system for pose and illumination invariant face recognition that combines two recent advances in the computer vision field: 3D morphable models and component-based recognition. A 3D morphable model is used to compute 3D face models from three input images of each subject in the training database. The 3D models are rendered under varying pose and illumination conditions to build a large set of synthetic images. These images are then used for training a component-based face recognition system. The face recognition module is preceded by a fast hierarchical face detector resulting in a system that can detect and identify faces in video images at about 4 Hz. The system achieved a recognition rate of 88% on a database of 2000 real images of ten people, which is significantly better than a comparable global face recognition system. The results clearly show the potential of the combination of morphable models and component-based recognition towards pose and illumination invariant face recognition.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6d45ab87e0f93006a53769e52fcd508c91d69083

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments (2008, background): “MIT-CBCL Face Recognition Database 10 > 2000 synthetic images from 3D models, illumination, pose, background [37]”
An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition (2007, methodology): “Other examples include the flexible appearance model-based method in [23] and [17].”