In this work we describe experiments with eigenfaces for recognition and interactive search in a large-scale face database. Accurate visual recognition is demonstrated using a database of o(10^3) faces. The problem of recognition under general viewing orientation is also explained. A view-based multiple-observer eigenspace technique is proposed for use in face recognition under variable pose. In addition, a modular eigenspace description technique is used which incorporates salient features such as the eyes, nose, mouth, in a eigenfeature layer. This modular representation yields higher recognition rates as well as a more robust framework for face recognition. An automatic feature extraction technique using feature eigentemplates is also demostrated.

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition and coding. Our learning technique is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and non-rigid objects such as hands.

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for a unimodal distribution) and a multivariate Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition. This learning technique is tested in experiments with modeling and subsequent detection of human faces and non-rigid objects such as hands.

In this paper we describe experiments using eigenfaces for recognition and interactive search in the FERET face database. A recognition accuracy of 99.35% is obtained using frontal views of 155 individuals. This figure is consistent with the 95% recognition rate obtained previously on a much larger database of 7,562 "mugshots" of approximately 3,000 individuals, consisting of a mix of all age and ethnic groups. We also demonstrate that we can automatically determine head pose without significantly lowering recognition accuracy; this is accomplished by use of a viewbased multiple-observer eigenspace technique. In addition, a modular eigenspace description is used which incorporates salient facial features such as the eyes, nose and mouth, in an eigenfeature layer. This modular representation yields slightly higher recognition rates as well as a more robust framework for face recognition. In addition, a robust and automatic feature detection technique using eigentemplates is demonstra...

Finding human faces automatically in an image is a difficult yet important first step to a fully automatic face recognition system. It is also an interesting academic problem because a successful face detection system can provide valuable insight on how one might approach other similar object and pattern detection problems. This paper presents an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face" and "non-face" prototype clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector, whether or not a human face exists at the current image location. We show empirically that the prototypes we choose for our distribution-based model, and the distance metric we adopt for computing difference featur...

We present a fully automatic system for 2D model-based image coding of human faces for potential applications such as video telephony, database image compression, and face recognition. The system operates by locating a face in the input image, normalizing its scale and geometry and representing it in terms of a parametric image model obtained with a Karhunen-Loeve basis. This leads to a compact representation of the face that can be used for both recognition as well as image compression. Good-quality facial images are automatically generated using approximately 100-bytes worth of encoded data. The system has been successfully tested on a database of nearly 2000 facial photographs.

We present an unsupervised technique for visual target modeling which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. A computationally efficient and optimal estimator for a multivariate Gaussian distribution is derived. This density estimate is then used to formulate a maximum likelihood estimation framework for visual search and target detection. Our learning technique is applied to the probabilistic visual modeling and subsequent detection of facial features and is shown to be superior to matched filtering.

Finding human faces automatically in an image is a difficult yet important first step to a fully automatic face recognition system. This paper presents an examplebased learning approach for locating unoccluded frontal views of human faces in complex scenes. The technique represents the space of human faces by means of a few view-based "face" and "non-face" pattern prototypes. At each image location, a 2-value distance measure is computed between the local image pattern and each prototype. A trained classifier determines, based on the set of distance measurements, whether a human face exists at the current image location. We show empirically that our distance metric is critical for the success of our system.

We present a distribution-based modeling cum example-based learning approach for detecting human faces in cluttered scenes. The distributionbased model captures complex variations in human face patterns that cannot be adequately described by classical pictorial template-based matching techniques or geometric model-based pattern recognition schemes. We also show how explicitly modeling the distribution of certain "facelike " non-face patterns can help improve classification results. 1 Introduction Finding human faces automatically in a cluttered image is an important first step to a fully automatic face recognition system. It also has many potential applications ranging from surveillance and census systems to humancomputer interfaces. Human face detection is difficult because there can be huge variations in the appearance of face patterns. Because many of these variations are difficult to parameterize, traditional fixed template pattern matching techniques [2] [3] and geometrical model...