Parameter optimization in approximating curves and surfaces to measurement data
Computer Aided Geometric Design
A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Object modelling by registration of multiple range images
Image and Vision Computing - Special issue: range image understanding
Iterative point matching for registration of free-form curves and surfaces
International Journal of Computer Vision
Surface fitting with hierarchical splines
ACM Transactions on Graphics (TOG)
Fitting smooth surfaces to dense polygon meshes
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Automatic reconstruction of B-spline surfaces of arbitrary topological type
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
A survey of free-form object representation and recognition techniques
Computer Vision and Image Understanding
Model Acquisition by Registration of Multiple Acoustic Range Views
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Face Modeling and Recognition in 3-D
AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition
Computer Vision and Image Understanding
| Hi-index | 0.00 |
This paper presents a new approach to automatic 3D face recognition using a model-based approach. This work uses real 3D dense point cloud data acquired with a scanner using a stereo photogrammetry technique. Since the point clouds are in varied orientations, by applying a non-iterative registration method, we automatically transform each point cloud to a canonical position. Unlike the iterative ICP algorithm, our non-iterative registration process is scale invariant. An efficient B-spline surface-fitting technique is developed to represent 3D faces in a way that allows efficient surface comparison. This is based on a novel knot vector standardisation algorithm which allow a single BSpline surface to be fitted onto a complex object represented as a unstructured points cloud. Consequently, dense correspondences across objects are established. Several experiments have been conducted and 91% recognition rate can be achieved.