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.

Researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing human faces for the last 20 years. While some systems, especially template-based ones, have been quite successful on expressionless, frontal views of faces with controlled lighting, not much work has taken face recognizers beyond these narrow imaging conditions. Our goal is to build a face recognizer that works under varying pose, the difficult part of which is to handle face rotations in depth. Building on successful template-based systems, our basic approach is to represent faces with templates from multiple model views that cover different poses from the viewing sphere. To recognize a novel view, the recognizer locates the eyes and nose features, uses these locations to geometrically register the input with model views, and then uses correlation on model templates to find the best match in the data base of people. Our system has achieved a recognition rate of 98% on a data base...

We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first locate facial components, extract them and combine them into a single feature vector which is classified by a Support Vector Machine (SVM). The two global systems recognize faces by classifying a single feature vector consisting of the gray values of the whole face image. In the first global system we trained a single SVM classifier for each person in the database. The second system consists of sets of viewpoint-specific SVM classifiers and involves clustering during training. We performed extensive tests on a database which included faces rotated up to about 40° in depth. The component system clearly outperformed both global systems on all tests.

Effective Human--to--Human communication involves both auditory and visual modalities, providing robustness and naturalness in realistic communication situations. Recent efforts at our lab are aimed at providing such multimodal capabilities for human-machine communication as well by introducing gesture, character and speech recognition, eye-tracking and lipreading. Most of the visual modalities require a stable image of a speaker's face. In this technical report a connectionist face tracker is proposed that manipulates camera orientation and zoom, to keep a person's face located at all times in an image sequence. The system operates in real time and can adapt rapidly to different lighting conditions, different cameras and faces, making it robust against environmental variability. Extensions and integration of the system with a multimodal interface will be presented. Contents 1 Introduction 1 1.1 Overview on the Face Tracking System : : : : : : : : : : : : : 2 1.2 Approach and Chapte...

The problem of dimension reduction is introduced as a way to overcome the curse of the dimensionality when dealing with vector data in high-dimensional spaces and as a modelling tool for such data. It is defined as the search for a low-dimensional manifold that embeds the high-dimensional data. A classification of dimension reduction problems is proposed. A survey of several techniques for dimension reduction is given, including principal component analysis, projection pursuit and projection pursuit regression, principal curves and methods based on topologically continuous maps, such as Kohonen’s maps or the generalised topographic mapping. Neural network implementations for several of these techniques are also reviewed, such as the projection pursuit learning network and the BCM neuron with an objective function. Several appendices complement the mathematical treatment of the main text.

this paper is to attempt to bring together people, results and questions from these three different disciplines -- HCI, AI, and Cognitive Science -- to explore the potential of building computer interfaces which understand and respond to the richness of the information conveyed in the human face. Until recently, information has been conveyed from the computer to the user mainly via the visual channel, whereas inputs from the user to the computer have been made from the keyboard and pointing devices via the user's motor channel. The recent emergence of multimodal interfaces as our everyday tools might restore a better balance between our physiology and sensory/motor skills, and impact (for the better we hope), the richness of activities we will find ourselves involved in. Given recent progress in user-interface primitives composed of gesture, speech, context and affect, it seems feasible to design environments which do not impose themselves as computer environments, but have a much more natural feeling associated with them.

Abstract—Most classical template-based frontal face recognition techniques assume that multiple images per person are available for training, while in many real-world applications only one training image per person is available and the test images may be partially occluded or may vary in expressions. This paper addresses those problems by extending a previous local probabilistic approach presented by Martinez, using the self-organizing map (SOM) instead of a mixture of Gaussians to learn the subspace that represented each individual. Based on the localization of the training images, two strategies of learning the SOM topological space are proposed, namely to train a single SOM map for all the samples and to train a separate SOM map for each class, respectively. A soft nearest neighbor (soft-NN) ensemble method, which can effectively exploit the outputs of the SOM topological space, is also proposed to identify the unlabeled subjects. Experiments show that the proposed method exhibits high robust performance against the partial occlusions and variant expressions. Index Terms—Face expression, face recognition, occlusion, selforganizing map (SOM), single training image per person.

ermine how the reliability of sex discrimination is related to resolution. A normalized pixel-based representation was used for the faces because it explicitly retained texture and shape information while also maintaining geometric relationships. We found that the linear perceptron model can classify sex from facial images with 81% accuracy, compared to 92% accuracy with compression coding on the same data set [6]. The advantage of using a simple linear perceptron with normalized pixel-based inputs is that it allows us to see explicitly those regions of the face that make the largest and most reliable contributions to the classification of sex. A database of 90 faces (44 males, 46 females) was used (O'Toole, Millward, & Anderson [9]). No facial hair, jewelry, or makeup was on any of the faces. Each face was rotated until the eyes were level, and then scaled and cropped so that each image showed a similar facial area. From the original set of faces, we created 5 separate databases at 5

Abstract not found

In order for mobile robots to interact e ectively with people they will have to recognize faces. In this paper we describe arobot system that nds people, approaches them and then recognizes them. The system uses a variety of techniques: color vision is used to ndpeople� vision and sonar sensors are used toapproach them � a template-based pattern recognition algorithm is used to isolate the face � and a neural network is used torecognize the face. All of these processes are controlled using an intelligent robot architecture thatsequences and monitors the robot's actions. We present the results of many experimental runs using an actual mobile robot nding and recognizing up to six di erent people.