We report the results of a comparative study on subspace analysis methods for face recognition. In particular, we have studied four different subspace representations and their 'kernelized' versions if available. They include both unsupervised methods such as principal component analysis (PCA) and independent component analysis (ICA), and supervised methods such as Fisher discriminant analysis (FDA) and probabilistic PCA (PPCA) used in a discriminative manner. The 'kernelized' versions of these methods provide subspaces of high-dimensional feature spaces induced by non-linear mappings. To test the effectiveness of these subspace representations, we experiment on two databases with three typical variations of face images, i.e, pose, illumination and facial expression changes. The comparison of these methods applied to different variations in face images offers a comprehensive view of all the subspace methods currently used in face recognition.

We report the results of a comparative study on subspace analysis methods for face recognition. In particular, we have studied four different subspace representations and their 'kernelized' versions if available. They include both unsupervised methods such as principal component analysis (PCA) and independent component analysis (ICA), and supervised methods such as Fisher discriminant analysis (FDA) and probabilistic PCA (PPCA) used in a discriminative manner. The 'kernelized' versions of these methods provide subspaces of high-dimensional feature spaces induced by non-linear mappings. To test the effectiveness of these subspace representations, we experiment on two databases with three typical variations of face images, i.e., pose, illumination and facial expression changes. The comparison of these methods applied to different variations in face images offers a comprehensive view of all the subspace methods currently used in face recognition.

In this paper we present the results of a comparative study of linear and kernel-based methods for face recognition. The methods used for dimensionality reduction are Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), Linear Discriminant Analysis (LDA) and Kernel Discriminant Analysis (KDA). The methods used for classification are Nearest Neighbor (NN) and Support Vector Machine (SVM). In addition, these classification methods are applied on raw images to gauge the performance of these dimensionality reduction techniques. All experiments have been performed on images from UMIST Face Database.

Aerial monitoring of ground sites using video cameras is playing an increasingly important role in autonomous surveillance applications. In such tasks it is important to be able to relate the activities detected in the video sequence to the 3D world, typically represented by a map, orthoimage or site model. Traditional image positioning approaches are generally not applicable to the real-time processing of (typically) low-resolution aerial video. The paper presents an approach to the automatic registration of aerial video to a site model. Low precision metadata are used to initialize the registration, and the resulting registration error is modeled as a simple translational shift. An operator-selected site feature is automatically tracked using frame stabilization parameters, and in each frame the registration error is corrected using the discrepancy between the metadata-predicted and tracked feature locations. This system runs on a PC in real time using less than 2% of the CPU. It has been demonstrated on real data obtained live during several flight experiments.

We describe a framework for aligning images without needing to establish explicit feature correspondences. We assume that the geometry between the two images can be adequately described by an affine transformation and develop a framework that uses the statistical distribution of geometric properties of image contours to estimate the relevant transformation parameters. The estimates obtained using the proposed method are robust to illumination conditions, sensor characteristics, etc., since image contours are relatively invariant to these changes. Moreover, the distributional nature of our method alleviates some of the common problems due to contour fragmentation, occlusion, clutter, etc. We provide empirical evidence of the accuracy and robustness of our algorithm. Finally, we demonstrate our method on both real and synthetic images, including multisensor image pairs.

Pattern comparison and pattern alignment are related tasks. The former requires the use of a similarity measure for discriminating between patterns of different classes, while the latter requires a measure of the degree of alignment of two similar patterns. This paper presents an experimental evaluation of two promising measures, Fourier phase correlation and mutual information, which can be used for quantifying the similarity as well as the degree of alignment of two patterns. It is shown that these measures are quite stable to a range of pattern intensity variations, while exhibiting gradual monotonic decrease in the presence of geometric transformations. Phase correlation is more resistant to pattern noise and interference, whereas mutual information is more resistant to intensity variations and geometric distortions.

We describe a framework for image alignment that does not use explicit feature correspondences. We show how certain geometric properties of image contours are related to the parameters of the geometric transformation between the images. For a transformation model, we show how to recover the transformation parameters using simple statistical distributions of geometric properties. The use of these statistical descriptions eliminates the need for establishing explicit feature correspondence. The proposed method is robust to problems of occlusion, clutter and errors in low-level processing. We demonstrate the effectiveness of our method on real images.

Modern image exploitation tasks have evolved from the early single-image, pixel-based and model-less methods to the current multi-image, multisensor, multiplatform, and model-based approaches. In this context, image positioning, which is the process of establishing the precise geometric relationship of an acquired image to the three-dimensional (3-D) world, has become an enabling technique for state-of-the-art multisensor data exploitation. Precise image positioning provides several benefits. Image registration, traditionally formulated as an image-to-image alignment problem, can now be carried out in accordance with interior and exterior sensor geometries. Images from sensors in arbitrary locations and orientations can be positioned with respect to a focal vertical and geocentric coordinate systems. This paper presents techniques for positioning images derived from various sensors such as electro-optical (E-O), synthetic aperture radar (SAR), and interferometric synthetic aperture radar (IFSAR). Applications to model-supported image exploitation are also discussed.

This paper deals with the integration of image understanding (IU) programs using a knowledge-based approach. The basic concepts of program integration are discussed, and a simple problem-solving model for program integration is outlined. Two types of reasoning, planning and execution control, are identified. A system developed using this model, called OCAPI (Optimizing, Controlling and Automating the Processing of Images), is introduced. OCAPI is an AI environment in which the reasoning used by the IU specialist is formally represented using frames and production rules. An example of the application developed using OCAPI is presented, and the advantages and shortcomings of this approach are discussed.

The authors present an approach to feature detection, which is a fundamental issue in many intermediate-level vision problems such as stereo, motion correspondence, image registration, etc. The approach is based on a scale-interaction model of the end-inhibition property exhibited by certain cells in the visual- cortex of mammals. These feature detector cells are responsive to short lines, line endings, corners and other such sharp changes in curvature. In addition, this method also provides a compact representation of feature information which is useful in shape recognition problems. Application to face recognition and motion correspondence are illustrated.>