We wish to determine the epipolar geometry of a stereo camera pair from image measurements alone. This paper describes a solution to this problem which does not require a parametric model of the camera system, and con...
详细信息
We wish to determine the epipolar geometry of a stereo camera pair from image measurements alone. This paper describes a solution to this problem which does not require a parametric model of the camera system, and consequently applies equally well to a wide class of stereo configurations. Examples in the paper range from a standard pinhole stereo configuration to more exotic systems combining curved mirrors and wide-angle lenses. The method described here allows epipolar curves to be learnt from multiple image pairs acquired by stereo cameras with fixed configuration. By aggregating information over the multiple image pairs, a dense map of the epipolar curves can be determined on the images. The algorithm requires a large number of images, but has the distinct benefit that the correspondence problem does not have to be explicitly solved. We show that for standard stereo configurations the results are comparable to those obtained from a state of the art parametric model method, despite the significantly weaker constraints on the non-parametric model. The new algorithm is simple to implement, so it may easily be employed on a new and possibly complex camera system.
Principal component analysis has proven to be useful for understanding geometric variability in populations of parameterized objects. The statistical framework is well understood when the parameters of the objects are...
详细信息
Principal component analysis has proven to be useful for understanding geometric variability in populations of parameterized objects. The statistical framework is well understood when the parameters of the objects are elements of a Euclidean vector space. This is certainly the case when the objects are described via landmarks or as a dense collection of boundary points. We have been developing representations of geometry based on the medial axis description or m-rep. Although this description has proven to be effective, the medial parameters are not naturally elements of a Euclidean space. In this paper we show that medial descriptions are in fact elements of a Lie group. We develop methodology based on Lie groups for the statistical analysis of medially-defined anatomical objects.
Libraries and other institutions are interested in providing access to scanned versions of their large collections of handwritten historical manuscripts on electronic media. Convenient access to a collection requires ...
详细信息
Libraries and other institutions are interested in providing access to scanned versions of their large collections of handwritten historical manuscripts on electronic media. Convenient access to a collection requires an index, which is manually created at great labour and expense. Since current handwriting recognizers do not perform well on historical documents, a technique called word spotting has been developed: clusters with occurrences of the same word in a collection are established using image matching. By annotating "interesting" clusters, an index can be built automatically. We present an algorithm for matching handwritten words in noisy historical documents. The segmented word images are reprocessed to create sets of 1-dimensional features, which are then compared using dynamic time warping. We present experimental results on two different data sets from the George Washington collection. Our experiments show that this algorithm performs better and is faster than competing matching techniques.
In this paper, we address the stereo matching problem in the presence of reflections and translucency, where image formation can be modeled as the additive superposition of layers at different depth. The presence of s...
详细信息
In this paper, we address the stereo matching problem in the presence of reflections and translucency, where image formation can be modeled as the additive superposition of layers at different depth. The presence of such effects violates the Lambertian assumption underlying traditional stereo vision algorithms, making it impossible to recover component depths using direct color matching based methods. We develop several techniques to estimate both depths and colors of the component layers. Depth hypotheses are enumerated in pairs, one from each layer, in a nested plane sweep. For each pair of depth hypotheses, we compute a component-color-independent matching error per pixel, using a spatial-temporal-differencing technique. We then use graph cut optimization to solve for the depths of both layers. This is followed by an iterative color update algorithm whose convergence is proven in our paper. We show convincing results of depth and color estimates for both synthetic and real image sequences.
A novel approach for tracking 3D articulated human bodies in stereo images is presented. We present a projection-based method for enforcing articulated constraints. We define the articulated motion space as the space ...
详细信息
Using a novel data dimension reduction method proposed in statistics, we develop an appearance-based face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taki...
详细信息
Using a novel data dimension reduction method proposed in statistics, we develop an appearance-based face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as coordinate in a high-dimensional space. However, since faces are not truly Lambertian surfaces and indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation using Sliced Inverse Regression (SIR) [9]. Our face recognition algorithm termed as Sirface produces well-separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expression. Sirface can be shown to be equivalent to the well known Fisherface algorithm [1] in the subspace sense. However, Sirface is shown to produce the optimal reduced subspace (with the fewest dimensions) resulting in a lower error rate and reduced computational expense. Experimental results comparing Sirface to Fisherface on the Yale face database are presented.
Most filter cigarettes today employ ventilated filters. Heavily ventilated filters have been found to be "elastic" in that they contribute to lower tar numbers in standard smoking-machine tests while at the ...
详细信息
ISBN:
(纸本)0780377893
Most filter cigarettes today employ ventilated filters. Heavily ventilated filters have been found to be "elastic" in that they contribute to lower tar numbers in standard smoking-machine tests while at the same time allowing smokers to get much higher doses of tar from the same cigarette when they block vents with fingers or lips. This paper describes a method for automating a Stain pattern technique which permits unobtrusive measurement of behavioral vent blocking. This automation could provide a more accurate analysis of filter efficacy. The system employs imageprocessing.and analysis to generate a set of unbiased features which are subsequently categorized by a fuzzy set based classifier.
Multilinear algebra, the algebra of higher-order tensors, offers a potent mathematical framework for analyzing ensembles of images resulting from the interaction of any number of underlying factors. We present a dimen...
详细信息
Multilinear algebra, the algebra of higher-order tensors, offers a potent mathematical framework for analyzing ensembles of images resulting from the interaction of any number of underlying factors. We present a dimensionality reduction algorithm that enables subspace analysis within the multilinear framework. This N-mode orthogonal iteration algorithm is based on a tensor decomposition known as the N-mode SVD, the natural extension to tensors of the conventional matrix singular value decomposition (SVD). We demonstrate the power of multilinear subspace analysis in the context of facial image ensembles, where the relevant factors include different faces, expressions, viewpoints, and illuminations. In prior work we showed that our multilinear representation, called TensorFaces, yields superior facial recognition rates relative to standard, linear (PCA/eigenfaces) approaches. Here, we demonstrate factor-specific dimensionality reduction of facial image ensembles. For example, we can suppress illumination effects (shadows, highlights) while preserving detailed facial features, yielding a low perceptual error.
We introduce two appearance-based methods for clustering a set of images of 3-D objects, acquired under varying illumination conditions, into disjoint subsets corresponding to individual objects. The first algorithm i...
详细信息
We introduce two appearance-based methods for clustering a set of images of 3-D objects, acquired under varying illumination conditions, into disjoint subsets corresponding to individual objects. The first algorithm is based on the concept of illumination cones. According to the theory, the clustering problem is equivalent to finding convex polyhedral cones in the high-dimensional image space. To efficiently determine the conic structures hidden in the image data, we introduce the concept of conic affinity which measures the likelihood of a pair of images belonging to the same underlying polyhedral cone. For the second method, we introduce another affinity measure based on image gradient comparisons. The algorithm operates directly on the image gradients by comparing the magnitudes and orientations of the image gradient at each pixel. Both methods have clear geometric motivations, and they operate directly on the images without the need for feature extraction or computation of pixel statistics. We demonstrate experimentally that both algorithms are surprisingly effective in clustering images acquired under varying illumination conditions with two large, well-known image data sets.
The goal of this paper is to present an algorithm for terrain matching, leveraging an existing fuzzy clustering algorithm, and modifying it to its supervised version, in order to apply the algorithm to georegistration...
详细信息
ISBN:
(纸本)0780379187
The goal of this paper is to present an algorithm for terrain matching, leveraging an existing fuzzy clustering algorithm, and modifying it to its supervised version, in order to apply the algorithm to georegistration and, later on patternrecognition. Georegistration is the process of adjusting one drawing or image to the geographic location of a "known good" reference drawing, image, surface or map. The georegistration problem can be treated as a patternrecognition problem;and it can be applied to the target detection problem. The terrain matching algorithm will be based on fuzzy set theory as a very accurate method to represent the imprecision of the real world, and presented as a multicriteria decision making problem. The energy emitted and reflected by the Earth's surface has to be recorded by relatively complex remote sensing devices that have spatial, spectral and geometrical resolution constraints. Errors usually slip into the data acquisition process. Therefore, it is necessary to preprocess the remotely sensed data, prior to analyzing it (image restoration, involving the correction of distortion, degradation and noise introduced during the rendering process). In this paper we shall assume that all these problems have been solved, focusing our study on the image classification of a corrected image being close enough, both geometrically and radiometrically, to the radiant energy characteristics of the target scene. In particular, at a first stage we consider each pixel individually;and a class will be assigned to each pixel, taking into account several values measured in separate spectral bands. Then we shall describe an automatic detection system based on a previous algorithm developed in A. Del Amo et al. [3, S], introducing now the fuzzy partition model proposed by A. Del Amo et al. [2, 4]. A first phase will lead to a spectral definition of patterns;and a second phase will lead to classification and recognition. Similarity measures will then allow us to
暂无评论