Catálogo de publicaciones - libros

Appearance-based modeling of objects and scenes using PCA has been successfully applied in many recognition tasks. Robust methods which have made the recognition stage less susceptible to outliers, occlusions, and varying illumination have further enlarged the domain of applicability. However, much less research has been done in achieving robustness in the learning stage. In this paper, we propose a novel robust PCA method for obtaining a consistent subspace representation in the presence of outlying pixels in the training images. The method is based on the EM algorithm for estimation of principal subspaces in the presence of missing data. By treating the outlying points as missing pixels, we arrive at a robust PCA representation. We demonstrate experimentally that the proposed method is efficient. In addition, we apply the method to a set of panoramic images to build a representation that enables surveillance and view-based mobile robot localization.

We propose a new learning approach for image retrieval, which we call , and demonstrate its use for face recognition and color matching. Our approach is motivated by a frequently encountered problem, namely, that variability in the original data representation which is not relevant to the task may interfere with retrieval and make it very difficult. Our key observation is that in real applications of image retrieval, data sometimes comes in small chunks - small subsets of images that come from the same (but unknown) class. This is the case, for example, when a query is presented via a short video clip. We call these groups , and we call the paradigm which uses chunklets for unsupervised learning . Within this paradigm we propose a linear scheme, which we call Relevant Component Analysis; this scheme uses the information in such chunklets to reduce irrelevant variability in the data while amplifying relevant variability. We provide results using our method on two problems: face recognition (using a database publicly available on the web), and visual surveillance (using our own data). In the latter application chunklets are obtained automatically from the data without the need of supervision.

Textons refer to fundamental micro-structures in generic natural images and thus constitute the basic elements in early (pre-attentive) visual perception. However, the word “texton” remains a vague concept in the literature of computer vision and visual perception, and a precise mathematical definition has yet to be found. In this article, we argue that the definition of texton should be governed by a sound mathematical model of images, and the set of textons must be learned from, or best tuned to, an image ensemble. We adopt a generative image model that an image is a superposition of bases from an over-complete dictionary, then a texton is defined as a mini-template that consists of a varying number of image bases with some geometric and photometric configurations. By analogy to physics, if image bases are like protons, neutrons and electrons, then textons are like atoms. Then a small number of textons can be learned from training images as repeating micro-structures. We report four experiments for comparison. The first experiment computes clusters in feature space of filter responses. The second use transformed component analysis in both feature space and image patches. The third adopts a two-layer generative model where an image is generated by image bases and image bases are generated by textons. The fourth experiment shows textons from motion image sequences, which we call movetons.

We consider image texture due to the illumination of 3D surface corrugations on globally smooth curved surfaces. The same surface corrugations give rise to different image textures depending on illumination and viewing geometries. We study surfaces that are on the average approximately Lambertian. The surface roughness gives rise to luminance modulations of the global shading pattern. The extreme values of the luminance depend on simple geometrical factors such as whether surface micro facets exist that squarely face the light source or are in shadow. We find that a simple microfacet-based model suffices to describe textures in natural scenes robustly in a semi-quantitative manner. Robust statistical measures of the texture yield the parameters for simple models that allow prediction of the BRDF. Thus texture analysis allows the input parameters for inverse rendering and material recognition to be estimated.

Illumination conditions cause problems for many computer vision algorithms. In particular, shadows in an image can cause segmentation, tracking, or recognition algorithms to fail. In this paper we propose a method to process a 3-band colour image to locate, and subsequently remove shadows. The result is a 3-band colour image which contains all the original salient information in the image, except that the shadows are gone.

We use the method set out in [] to derive a 1-d illumination invariant shadow-free image. We then use this invariant image together with the original image to locate shadow edges. By setting these shadow edges to zero in an edge representation of the original image, and by subsequently re-integrating this edge representation by a method paralleling lightness recovery, we are able to arrive at our sought after full colour, shadow free image. Preliminary results reported in the paper show that the method is effective.

A caveat for the application of the method is that we must have a calibrated camera. We show in this paper that a good calibration can be achieved simply by recording a sequence of images of a fixed outdoor scene over the course of a day. After calibration, only a single image is required for shadow removal. It is shown that the resulting calibration is close to that achievable using measurements of the camera’s sensitivity functions.