In the context of the appearance-based paradigm for object recognition, it is generally believed that algorithms based on LDA (Linear Discriminant Analysis) are superior to those based on PCA (Principal Components Analysis) . In this communication we show that this is not always the case. We present our case first by using intuitively plausible arguments and then by showing actual results on a face database. Our overall conclusion is that when the training dataset is small, PCA can outperform LDA, and also that PCA is less sensitive to different training datasets. Keywords: face recognition, pattern recognition, principal components analysis, linear discriminant analysis, learning from undersampled distributions, small training datasets. 1

In this paper we describe a holistic face recognition method based on subspace Linear Discriminant Analysis (LDA). The method consists of two steps: first we project the face image from the original vector space to a face subspace via Principal Component Analysis where the subspace dimension is carefully chosen, and then use LDA to obtain a linear classifier in the subspace. The criterion we use to choose the subspace dimension enables us to generate class-separable features via LDA. In addition, we employ a weighted distance metric guided by the LDA eigenvalues to improve the performance of the subspace LDA method. Finally, the improved performance of the subspace LDA approach is demonstrated through experiments using the FERET dataset for face recognition/verification, a large mugshot dataset for person verification, and the MPEG-7 dataset. 1 Partially supported by the Office of Naval Research under Grant N00014-95-1-0521. I. Introduction The problem of automatic face recognition...

A real-time vision system is described that can recognize 100 complex three-dimensional objects. In contrast to traditional strategies that rely on object geometry and local image features, the present system is founded on the concept of appearance matching. Appearance manifolds of the 100 objects were automatically learned using a computer-controlled turntable. The entire learning process was completed in 1 day. A recognition loop has been implemented that performs scene change detection, image segmentation, region normalizations, and appearance matching, in less than 1 second. The hardware used by the recognition system includes no more than a CCD color camera and a workstation. The real-time capability and interactive nature of the system have allowed numerous observers to test its performance. To quantify performance, we have conducted controlled experiments on recognition and pose estimation. The recognition rate was found to be 100 % and object pose was estimated with a mean abso...

This paper discusses region-based representations of image and video that are useful for multimedia services such as those supported by the MPEG-4 and MPEG-7 standards. Classical tools related to the generation of the region-based representations are discussed. After a description of the main processing steps and the corresponding choices in terms of feature spaces, decision spaces, and decision algorithms, the state of the art in segmentation is reviewed. Mainly tools useful in the context of the MPEG-4 and MPEG-7 standard are discussed. The review is structured around the strategies used by the algorithms (transition-based or homogeneity-based) and the decision spaces (spatial, spatio-temporal and temporal). The second part of the paper proposes a partition tree representation of images and introduces a processing strategy that involves a similarity estimation step followed by a partition creation step. This strategy tries to find a compromise between what can be done in...

In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. For any given vision task, all possible appearance variations define its visual workspace. A set of images is obtained by coarsely sampling the workspace. The image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the visual workspace is represented as a continuous appearance manifold. Given an unknown input image, the recognition system first projects the image to eigenspace. The parameters of the vision task are recognized based on the exact position of the projection on the appearance manifold. The proposed appearance representation has several applications in visual perception. As examples, a real-time recognition system with 20 complex objects, an illumination planning technique for robust object recognition, and a real-time visual positioning and tracking system are described. The simplicity and generality of the pr...

Abstract — When using appearance-based recognition for self-localization of mobile robots, the images obtained during the exploration of the environment need to be efficiently stored in the memory. PCA offers means for representing the images in a low-dimensional subspace, which allows for efficient matching and recognition. For active exploration it is necessary to use an incremental method for the computation of the subspace. While such methods have been considered before, only the on-line construction of eigenvectors has been addressed. Representations of the images in the subspace were computed only after the final subspace had been built, requiring that all the images were kept in the memory. In this paper we propose to use an incremental PCA algorithm with the updating of partial image representations in a way that allows the robot to discard the acquired images immediately after the update. Such a model is open-ended, meaning that we can easily update it with new images. We show that the performance of the proposed method is comparable to the performance of the batch method in terms of compression, computational cost and the precision of localization. We also show that by applying the repetitive learning, the subspace converges to that constructed with the batch method. Keywords—Robot localization, on-line visual learning, PCA updating, view-based robot localization, repetitive learning. I.

The paradigm for image based localization using panoramic images is elaborated. Panoramic images provide complete views of an environment and their information content does not change if a panoramic camera is rotated. The "zero phase representation" of cylindrical panoramic images, an example of a rotation invariant representation, is constructed for the class of images which have non-zero first harmonic in column direction. It is an invariant and fully discriminative representation. The zero phase representation is demonstrated by an experiment with real data and it is shown that the alternative autocorrelation representation is outperformed.

{ matjaz.jogan,alesl} @ frimi-lj.si The results of recent studies on the possibility of spa-tial localization from panoramic images have shown good prospects for view-based methods. The major advantages of these methods are a wide field-of-view, capability of mod-elling cluttered environments, and flexibility in the learning phase. The redundant information captured in similar views is efficiently handled by the eigenspace approach. However, the standard approaches are sensitive to noise and occlu-sion. In this paper, we present a method of view-based lo-calization in a robust framework that solves these problems to a large degree. Experimental results on a large set of real panoramic images demonstrate the effectiveness of the approach and the level of achieved robustness. 1. Introduction and

Under in-plane rotations of a panoramic camera, the information content of a panoramic image is, in general, preserved. However, different representations that can be derived have important implications on further processing, e.g. for appearance-based localization. We discuss several approaches based on different representations that have been proposed and evaluate them from different points-ofview, in particular, we argue that most of them are not suitable for robust localization under partially occluded views. In this paper we propose a representation---eigenspace of spinning-images---which enables a straightforward application of the robust estimation of eigenimage coefficients which is directly related to the localization.

Face images are subject to changes in view and illumination. Such changes cause data distribution to be highly nonlinear and complex in the image space. It is desirable to learn a nonlinear mapping from the image space to a low dimensional space such that the distribution becomes simpler, tighter and therefore more predictable for better modeling of faces. In this paper, we present a kernel machine based approach for learning such nonlinear mappings. The aim is to provide an effective view-based representation for multiview face detection and pose estimation. Assuming that the view is partitioned into a number of distinct ranges, one nonlinear view-subspace is learned for each (range of) view from a set of example face images of that view (range), by using kernel principal component analysis (KPCA). Projections of the data onto the view-subspaces are then computed as view-based nonlinear features. Multi-view face detection and pose estimation are performed by classifying a face into one of the facial views or into the nonface class, by using a multi-class kernel support vector classifier (KSVC). Experimental results show that fusion of evidences from multiviews can produce better results than using the result from a single view; and that our approach yields high detection and low false alarm rates in face detection and good accuracy in pose estimation, in comparison with the linear counterpart composed of linear principal component analysis (PCA) feature extraction and Fisher linear discriminant based classification (FLDC).