An experimental comparison of RGB, YIQ, LAB, HSV, and opponent color models
ACM Transactions on Graphics (TOG)
Inference and retrieval of facial images
Multimedia Systems
SpotIt! An interactive identikit system
Graphical Models and Image Processing
Design galleries: a general approach to setting parameters for computer graphics and animation
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
An anthropometric face model using variational techniques
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
The mug-shot search problem: a study of the eigenface metric, search strategies, and interfaces in a system for searching facial image data
A biologically inspired generation of virtual characters
Proceedings of the 2008 ACM symposium on Applied computing
EDFCES: a new example-driven 3D face construction and editing system
Machine Graphics & Vision International Journal
Face to face: anthropometry-based interactive face shape modeling using model priors
International Journal of Computer Games Technology - Special issue on cyber games and interactive entertainment
Data-driven feature control models for creating virtual faces
ICCSA'07 Proceedings of the 2007 international conference on Computational science and Its applications - Volume Part II
SBM'08 Proceedings of the Fifth Eurographics conference on Sketch-Based Interfaces and Modeling
Hi-index | 0.00 |
We have created a gradient-based face navigation interface that allows users to explore a large face space based on an eigenface technique. This approach to synthesizing faces contrasts with more typical techniques for forming composite faces based on the blending of facial features. We compare three ways of moving through the face space, using two types of sliders and a face-wheel. These are adapted from typical color space interfaces since they are commonly used. However, eigenface dimensions do not have meaningful text labels, unlike primary colors, necessitating the use of faces themselves for the labels of the navigation axes. Results suggest that users can navigate with face-labelled axes. They find slider interfaces best suited to finding the neighborhood of a target face, but that the face-wheel is better for refinement once inside the neighborhood.