Low-dimensional procedure for the characterization of human faces

Sirovich, Lawrence; Kirby, Michael

doi:10.1364/josaa.4.000519

Cited by 1,921 publications

(922 citation statements)

References 2 publications

Supporting

Mentioning

896

Contrasting

Unclassified

Order By: Relevance

“…Although statistical face modelling started earlier (see for example [32]), [28] is widely regarded as the inauguration of face modelling. The model is built from a set of k 2D frontal images.…”

Section: Modelsmentioning

confidence: 99%

“…Whether in 2D (eye-centre-aligned [32] or shape-free, warped images [73]) or 3D (depth maps [74], fields of surface normals [17] or meshes in dense correspondence [9]), human faces have been shown to be highly amenable to description using a linear statistical model. 2D approaches model appearance directly, with the training data capturing both extrinsic scene properties (such as illumination and camera parameters) and intrinsic face properties (geometry and reflectance properties).…”

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Inverse Rendering of Faces with a 3D Morphable Model

Aldrian

Smith

2013

IEEE Trans. Pattern Anal. Mach. Intell.

179

160

View full text Add to dashboard Cite

In this thesis, we present a complete framework to inverse render faces with a 3D Morphable Model. By decomposing the image formation process into a geometric and photometric part, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a globally optimal solution can be found. We start by recovering 3D shape using a novel algorithm which incorporates generalisation errors of the model obtained from empirical measurements. The algorithm is extended so it can efficiently deal with mixture distributions. We then describe three methods to recover facial texture, and for the second and third, diffuse lighting, specular reflectance and camera properties from a single image. These methods make increasingly weak assumptions and can all be solved in a linear fashion. We further modify our framework so it accounts for global illumination effects. This is achieved by incorporating statistical models for ambient occlusion and bent normals into the image formation model. We show that solving for ambient occlusion and bent normal parameters as part of the fitting process improves the accuracy of the estimated texture map and illumination environment. We present results on challenging data, rendered under complex natural illumination with both specular reflectance and occlusion of the illumination environment. We evaluate our findings on publicly available datasets, where we are able to obtain state-ofthe-art results. Finally, we present a practical method to synthesise a larger population from a small training-set and show how the new instances can be used to build a flexible PCA model.

show abstract

Section: Modelsmentioning

confidence: 99%

Section: State Of the Artmentioning

confidence: 99%

Inverse Rendering of Faces with a 3D Morphable Model

Aldrian

Smith

2013

IEEE Trans. Pattern Anal. Mach. Intell.

179

160

View full text Add to dashboard Cite

show abstract

“…It reduces the dimensionality of the description by projecting the points onto the principal axes, where orthonormal set of points are in the direction of maximum covariance of the data. PCA is an optimal compression scheme that minimizes the mean squared error between the original images and their reconstructions for any given level of compression [23,24]. works by finding a new coordinate system for a set of data, where the axes (or principal components) are ordered by the variance contained within the training data [25].The approach for face recognition aims is decompose face images into small set of characteristic feature images called eigenfaces which used to represent both existing and new faces.…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

Face Recognition System Using PCA and DCT in HMM

Jameel¹

2015

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:The speed of procedures became necessities during recent years; therefore using computers turn out to be the most important factors to increase the speed of implementation especially in security aspect such as recognition of people.There are a lot of waysto recognize the people face recognition is one of them. In this work the details of the face have been taken as blocks and Discrete Cosine Transform (DCT) is used, applied on face image's blocks. Then without doing inverse DCT Principal Component Analysis (PCA) is applied directly for dimensionality reduction this makes the system very fast. Olivetti Research Laboratory (ORL) database of faces had been used to obtain the results.Each face is considered as a numerical sequence (blocks) that can be easily modelled by HMM. On 400 face images of the (ORL) face database the system has been examined. The experiments showed a recognition rate of 95.211%, using half of the images for training.

show abstract

“…Sirovich and Kirby [8,9] evaluated a limited version of this framework on an ensemble of 115 images (M = 115) images of Caucasian males digitized in a controlled manner, and found that 40 eigenfaces were sufficient for a very good description of face images. In practice, a smaller M' can be sufficient for identification, since accurate reconstruction of the image is not a requirement.…”

Section: Using Eigenfaces To Classify a Face Imagementioning

confidence: 99%

Face Recognition System Based on PCA and Feedforward Neural Networks

Eleyan

Demirel

2005

Computational Intelligence and Bioinspired Systems

View full text Add to dashboard Cite

Abstract. Face recognition is one of the most important image processing research topics which is widely used in personal identification, verification and security applications. In this paper, a face recognition system, based on the principal component analysis (PCA) and the feedforward neural network is developed. The system consists of two phases which are the PCA preprocessing phase, and the neural network classification phase. PCA is applied to calculate the feature projection vector of a given face which is then used for face identification by the feedforward neural network. The proposed PCA and neural network based identification system provides improvement on the recognition rates, when compared with a face classifier based on the PCA and Euclidean Distance.

show abstract

Low-dimensional procedure for the characterization of human faces

Cited by 1,921 publications

References 2 publications

Inverse Rendering of Faces with a 3D Morphable Model

Inverse Rendering of Faces with a 3D Morphable Model

Face Recognition System Using PCA and DCT in HMM

Face Recognition System Based on PCA and Feedforward Neural Networks

Contact Info

Product

Resources

About