When recognizing a fixed object from a fixed viewpoint, the dominant source of variation in image intensity is lighting changes. We propose a low-dimensional model for human faces that can both synthesize a face image when given lighting conditions and can estimate lighting conditions when given a face image. The model can handle non-Lambertian and self-shadowing surfaces such as faces because it does not make any assumptions about either the surface geometry or bidirectional reflectance function. The model can be adapted to handle any arbitrary lighting condition, and is easily extendable to any other viewpoint or to any other object.>

A method for detecting and describing the features of faces using deformable templates is described. The feature of interest, an eye for example, is described by a parameterized template. An energy function is defined which links edges, peaks, and valleys in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image, by altering its parameter values to minimize the energy function, thereby deforming itself to find the best fit. The final parameter values can be used as descriptors for the features. This method is demonstrated by showing deformable templates detecting eyes and mouths in real images.>