A system of analyzing and synthesizing facial images

Choi, Chang Soo; Okazaki, T.; Harashima, Hiroshi; Takebe, Tsuyoshi

doi:10.1109/iscas.1991.176094

Cited by 25 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some algorithms match a small number of feature vertices to image positions, and interpolate deformations of the surface in between [21]. Others use restricted, but class-specific deformations, which can be defined manually [24], or learned from images [10], from nontextured [1] or textured 3D scans of heads [8].…”

Section: Introductionmentioning

confidence: 99%

Face recognition based on fitting a 3D morphable model

Blanz

Vetter

2003

IEEE Trans. Pattern Anal. Machine Intell.

1,806

1,255

View full text Add to dashboard Cite

Abstract-This paper presents a method for face recognition across variations in pose, ranging from frontal to profile views, and across a wide range of illuminations, including cast shadows and specular reflections. To account for these variations, the algorithm simulates the process of image formation in 3D space, using computer graphics, and it estimates 3D shape and texture of faces from single images. The estimate is achieved by fitting a statistical, morphable model of 3D faces to images. The model is learned from a set of textured 3D scans of heads. We describe the construction of the morphable model, an algorithm to fit the model to images, and a framework for face identification. In this framework, faces are represented by model parameters for 3D shape and texture. We present results obtained with 4,488 images from the publicly available CMU-PIE database and 1,940 images from the FERET database.

show abstract

Section: Introductionmentioning

confidence: 99%

Face recognition based on fitting a 3D morphable model

Blanz

Vetter

2003

IEEE Trans. Pattern Anal. Machine Intell.

1,806

1,255

View full text Add to dashboard Cite

show abstract

“…Choi developed a system to analyze features of shapes and textures and synthesize the facial images [7,8]. He later employed a 3D facial shape model (FSM) to separate the facial image into the facial shape and the skin color.…”

Section: • Physical Approachesmentioning

confidence: 99%

Synthesis of 3D Aging Faces Based on Color Gabor Wavelet and Texture Transplant

Hui-lin

Kong

Yin

2009

2009 International Conference on Computational Intelligence and Software Engineering

View full text Add to dashboard Cite

Facial aging synthesis is one of the main topics in computer graphics. This paper proposes a synthetic approach to 3D aging faces by using color gabor wavelet and texture transplant techniques. Based on 3D aging templates, the color gabor wavelet transform is carried out first to extract the highfrequency sub-images from the texture maps, in which is contained the texture feature of aging skin. Then the corresponding sub-images of target facial images are replaced and fused. The transplant of aging texture towards target face is finally achieved through wavelet reconstruction. The experimental results show that the aging features can be extracted effectively by wavelet transform and be used to synthesize the 3D aging face of the target face.

show abstract

“…Synthesis of new faces by interpolation between such face representation was already demonstrated in the pioneering work of Parke (1974). Recently the idea of forming linear combinations of faces has been used and extended to a general three-dimensional flexible face model for the analysis and synthesis of two-dimensional facial images [1,4].…”

Section: Three-dimensional Modelsmentioning

confidence: 99%

“…Recently, two-dimensional image-based face models have been constructed and applied for the synthesis of rigid and nonrigid face transformations [1,2,3]. These models exploit prior knowledge from example images of prototypical faces and work by building flexible image-based representations (active shape models) of known objects by a linear combination of labeled examples.…”

Section: Introductionmentioning

confidence: 99%

Estimating coloured 3D face models from single images: An example based approach

Vetter

Blanz

1998

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper we present a method to derive 3D shape and surface texture of a human face from a single image. The method draws on a general flexible 3D face model which is “learned” from examples of individual 3D-face data (Cyberware-scans). In an analysis-by-synthesis loop, the flexible model is matched to the novel face image. From the coloured 3D model obtained by this procedure, we can generate new images of the face across changes in viewpoint and illumination. Moreover, nonrigid transformations which are represented within the flexible model can be applied, for example changes in facial expression. The key problem for generating a flexible face model is the computation of dense correspondence between all given 3D example faces. A new correspondence algorithm is described which is a generalization of common algorithms for optic flow computation to 3D-face data

show abstract

A system of analyzing and synthesizing facial images

Cited by 25 publications

References 7 publications

Face recognition based on fitting a 3D morphable model

Face recognition based on fitting a 3D morphable model

Synthesis of 3D Aging Faces Based on Color Gabor Wavelet and Texture Transplant

Estimating coloured 3D face models from single images: An example based approach

Contact Info

Product

Resources

About