Caricature Generator: The Dynamic Exaggeration of Faces by Computer

  title={Caricature Generator: The Dynamic Exaggeration of Faces by Computer},
  author={Susan Brennan},
  pages={170 - 178}
The author has researched and developed a theory of computation for caricature and has implemented this theory as an interactive computer graphics program. The Caricature Generator program is used to create caricatures by amplifying the differences between the face to be caricatured and a comparison face. This continuous, parallel amplification of facial features on the computer screen simulates the visualization process in the imagination of the caricaturist. The result is a recognizable… Expand
Improved automatic caricature by feature normalization and exaggeration
This sketch presents an improved formalization of automatic caricature that extends a standard approach to account for the population variance of facial features to investigate caricaturerelated issues in face perception. Expand
Example-Based Automatic Caricature Generation
Experimental results show that the proposed example based automatic caricature generation system can achieve the control over the degree of exaggeration and the exaggerated results can better represent the features of the subjects. Expand
A Study on Perceived Similarity between Photograph and Shape Exaggerated Caricature
The experimental environment in this research can be used as a user-friendly caricature generation system based on Exaggerating the Difference From the Mean face, which allows a user to freely control each generation step and design his or her own unique caricature portrait. Expand
Human facial illustrations: Creation and psychophysical evaluation
These studies show that the facial illustrations and caricatures generated using the techniques presented are as effective as photographs in recognition tasks. Expand
Regularity-Based Caricature Synthesis
This paper presents a regularity-based caricature synthesis technique from a frontal face image, consisting of shape exaggeration, relationship exaggeration, and hierarchical- exaggeration model, which defines all facial proportions three hierarchy to guide exaggeration. Expand
Interactive 3D caricature from harmonic exaggeration
This work introduces a caricature tool that interactively emphasizes the differences between two three-dimensional meshes, represented in the manifold harmonic basis of the shape to be caricatured, providing intrinsic controls on the deformation and its scales. Expand
Mean value coordinates–based caricature and expression synthesis
A novel method for caricature synthesis based on mean value coordinates (MVC) that can be applied to any single frontal face image to learn a specified caricature face pair for frontal and 3D caricature synthesis and is extended to 3D caricatures based on the 3D version of MVC. Expand
Example Based Caricature Synthesis
An example based caricature synthesis technique, consisting of shape exaggeration, relationship exaggeration, and optimization for likeness, is presented, which allows us to optimize the configuration of facial elements, maximizing the likeness while satisfying a number of constraints. Expand
A Facial Caricature Generation system using Adaptive Thresholding
A novel approach of Adaptive Thresholding has been used for the extraction of feature points from theinput face to manage the non-uniform illuminations of the input face. Expand
Study of Generating Portraits Using Neural Networks
This paper proposes a method that can automatically generate portraits from face images (photos) using multi-layered neural networks, for which image features of the face are the inputs, the portraitExpand


On the Concept of ‘Formless Invariants’ in Visual Perception
It was first concluded from this experiment that such a sequence (or geometrical family) of optical forms was a 'stimulus' for the perception of the face of an object, and the term stimulus was being used in a very general sense. Expand
The Use of Faces to Represent Points in k- Dimensional Space Graphically
Every multivariate observation is visualized as a computer-drawn face that makes it easy for the human mind to grasp many of the essential regularities and irregularities present in the data. Expand