Abstract—Face images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression, and lighting. We describe a compact parametrized model of facial appearance which takes into account all these sources of variability. The model represents both shape and gray-level appearance, and is created by performing a statistical analysis over a training set of face images. A robust multiresolution search algorithm is used to fit the model to faces in new images. This allows the main facial features to be located, and a set of shape, and gray-level appearance parameters to be recovered. A good approximation to a given face can be reconstructed using less than 100 of these parameters. This representation can be used for tasks such as image coding, person identification, 3D pose recovery, gender recognition, and expression recognition. Experimental results are presented for a database of 690 face images obtained under widely varying conditions of 3D pose, lighting, and facial expression. The system performs well on all the tasks listed above.

Face images are difficult to interpret because they are highly variable. Sources of variability include individual appear# ance, 3D pose, facial expression and lighting. We describe a compact parametrised model of facial appearance which takes into account all these sources of variability. The model represents both shape and grey-level appearance and is created by performing a statistical analysis over a training set of face images. A robust multi-resolution search algo# rithm is used to fit the model to faces in new images. This allows the main facial features to be located and a set of shape and grey-level appearance parameters to be recov# ered. A good approximation to a given face can be recon# structed using less than 100 of these parameters. This repre# sentation can be used for tasks such as image coding, person identification, pose recovery, gender recognition and ex# pression recognition. The system performs well on all the tasks listed above. 1: Introduction Á ÂÄÀÅÃÇÂÉÀÊÅËÂÈ...

Face images and hand gestures provide a very ef# fective means of visual communication between humans. Similarly automatic face and gesture rec# ognition systems could be employed for contactless human-machine interaction systems. How# ever, developing such system is difficult, because faces and hands are both complex and highly vari# able structures. We describe how flexible models can be used to represent appearance variations of faces and hands and how these models can be used for tracking and interpretation. Experimental re# sults are presented for face pose recovery, face identification, expression recognition and gesture interpretation. 1 Introduction This paper addresses the problem of locating and interpreting faces and hand gestures in images. By interpreting face images we mean recovering the 3D pose, identifying the individual and recognising the expression; for the hand images we mean re# cognising the configuration of the fingers. In both cases different instances of the ...

The vast majority of work in machine vision emphasizes the representation of perceived objects and events: it is these internal representations that incorporate the `knowledge' in knowledge-based vision or form the `models' in model-based vision. In this paper, we discuss simple machine vision systems developed by artificial evolution rather than traditional engineering design techniques, and note that the task of identifying internal representations within such systems is made difficult by the lack of an operational definition of representation at the causal mechanistic level. Consequently, we

Detection of facial features is difficult because face images are highly variable. Sources of variability include individual appearance, 3D pose, facial expression and lighting. We describe a system for locating facial features, which uses flexible models of appearance as a means of providingprior knowledge about the expected appearance of j'katures and the spatial relationships between them. A global search procedure based on Genetic Algorithms is used to fit the model to new face images, so that the exact position of a face and facial features can be recovered.

Point Distribution Models (PDMs) are statistical models which represent objects whose shape can vary. A useful feature of PDMs is their ability to capture the shape of variable objects within a training set with a small number of shape parameters. This compact and accurate parametrization can be used for the design of efficient classification systems. In this paper we describe a classification system which uses shape parameters. We have tested the system on classifying hand outlines, face outlines and hand gestures; experimental results are presented.