Parametric face drawings: A demographically diverse and customizable face space model.

@article{Day2019ParametricFD,
  title={Parametric face drawings: A demographically diverse and customizable face space model.},
  author={Jennifer Day and Nicolas Davidenko},
  journal={Journal of vision},
  year={2019},
  volume={19 11},
  pages={
          7
        }
}
We introduce a novel face space model-parametric face drawings (or PFDs)-to generate schematic, though realistic, parameterized line drawings of faces based on the statistical distribution of human facial features. A review of existing face space models (including FaceGen Modeller, Synthetic Faces, MPI, and active appearance model) indicates that current models are constrained by their reliance on ethnically homogeneous face databases. This constraint has led to negative consequences for… 
1 Citations

Figures from this paper

Recommendations for Investigating the Cross-Category Effect Among Hispanic and Latino Populations.

  • Jennifer L. Rennels
  • Sociology
    Perspectives on psychological science : a journal of the Association for Psychological Science
  • 2022
Individuals who are Hispanic or Latino make up a substantial portion of the U.S. and world population yet are vastly underrepresented as both participants and stimuli in the face-perception

References

SHOWING 1-10 OF 33 REFERENCES

Physical and Psychological Representations of Faces: Evidence From Morphing

Models of face recognition and classification often adopt a framework in which faces are represented as points in a multidimensional space. This psychological face space organizes the faces according

Silhouetted face profiles: a new methodology for face perception research.

TLDR
A shape-based parameterization that relies on a small set of landmark points is described and it is shown that face silhouettes can be effectively represented in a 20-dimensional "silhouette face space" and that in this physical space, distance from the center of the space corresponds to perceived distinctiveness.

Facial analysis and synthesis using image-based models

  • T. EzzatT. Poggio
  • Computer Science
    Proceedings of the Second International Conference on Automatic Face and Gesture Recognition
  • 1996
TLDR
An analysis-by-synthesis algorithm is described, which is capable of extracting a set of high-level parameters from an image sequence involving facial movement using embedded image-based models.

A parametric model for human faces.

TLDR
This three-dimensional, parametric model produces shaded facial images and several animated sequences that illustrate the power of the model to change facial expression and conformation.

Bidirectional Gender Face Aftereffects: Evidence Against Normative Facial Coding

TLDR
It is shown that face gender aftereffects are bidirectional, which suggests that, rather than mental representations of all faces being recalibrated to better reflect the prevailing statistics of the environment, mental operations exaggerate differences between successive faces, and this can impact facial gender perception.

Physical and perceptual accuracy of upright and inverted face drawings

ABSTRACT This study considers the conception that drawing or copying a face that is vertically inverted will improve the accuracy of the drawing by preventing holistic interference. We used a novel

A Unified Account of the Effects of Distinctiveness, Inversion, and Race in Face Recognition

  • T. Valentine
  • Psychology
    The Quarterly journal of experimental psychology. A, Human experimental psychology
  • 1991
TLDR
It is argued that a multidimensional space provides a useful heuristic framework to investigate recognition of faces and that a norm-based coding version and the exemplar-based version of the framework cannot be distinguished on the basis of the experiments reported.

Attending to Race (or Gender) Does Not Increase Race (or Gender) Aftereffects

TLDR
The results suggest that attending to a facial dimension such as race or gender does not result in increased adaptation to that dimension, and aftereffects were not stronger along attention-congruent than attention-incongruent dimensions.