We present a platform for human-machine interfaces that provides functionality for robust, unencumbered interaction: the 4D Touchpad (4DT). The goal is direct interaction with interface components through intuitive ac...
详细信息
In this paper, we propose an ICA (Independent Component Analysis) based face recognition algorithm, which is robust to illumination and pose variation. Generally, it is well known that the first few eigenfaces represe...
详细信息
In this paper, we propose an ICA (Independent Component Analysis) based face recognition algorithm, which is robust to illumination and pose variation. Generally, it is well known that the first few eigenfaces represent illumination variation rather than identity. Most PCA (Principal Component Analysis)-based methods have overcome illumination variation by discarding the projection to a few leading eigenfaces. The space spanned after removing a few leading eigenfaces is called the "residual face space". We found that ICA in the residual face space provides more efficient encoding in terms of redundancy reduction and robustness to pose variation as well as illumination variation, owing to its ability to represent non-Gaussian statistics. Moreover, a face image is separated into several facial components, local spaces, and each local space is represented by the ICA bases (independent components) of its corresponding residual space. The statistical models of face images in local spaces are relatively simple and facilitate classification by a linear encoding. Various experimental results show that the accuracy of face recognition is significantly improved by the proposed method under large illumination and pose variations.
In this paper, we make use of the Beckmann-Kirchhoff and Davies scattering models to estimate surface properties for both dielectric and metallic surfaces based on reflectance measurements. In the case of metallic sur...
详细信息
In this paper, we make use of the Beckmann-Kirchhoff and Davies scattering models to estimate surface properties for both dielectric and metallic surfaces based on reflectance measurements. In the case of metallic surfaces, we consider two refinements of the Davies theory which apply under different restrictions concerning the reflectance geometry. The first of these is due to Bennett and Porteus and applies for normal incidence and reflectance. The second is due to Torrance and applies when the incidence radiation is off normal. We then suggest three classes of materials for which the appropriate approximations may be used to estimate the surface roughness, the correlation length and the surface slope. Finally, we use the surface slope estimates to fit the Beckmann-Kirchhoff model to reflectance data. In contrast to previous methods which work at long wavelengths and use special purpose instrumentation, our methods can be performed using visible light and a digital camera.
We introduce the problem of repetitive nearest neighbor search in relevance feedback and propose an efficient search scheme for high dimensional feature spaces. Relevance feedback learning is a popular scheme used in ...
详细信息
We introduce the problem of repetitive nearest neighbor search in relevance feedback and propose an efficient search scheme for high dimensional feature spaces. Relevance feedback learning is a popular scheme used in content based image and video retrieval to support high-level concept queries. This paper addresses those scenarios in which a similarity or distance matrix is updated during each iteration of the relevance feedback search and a new set of nearest neighbors is computed. This repetitive nearest neighbor computation in high dimensional feature spaces is expensive, particularly when the number of items in the data set is large. In this context, we suggest a search algorithm that supports relevance feedback for the general quadratic distance metric. The scheme exploits correlations between consecutive nearest neighbor sets thus significantly reducing the overall search complexity. Detailed experimental results are provided using 60 dimensional texture feature data set.
Range image analysis is one of the most important subjects in the fields of computer vision and patternrecognition, and range image segmentation is the key of the analysis. This paper presents a range image segmentat...
详细信息
ISBN:
(纸本)0780381858
Range image analysis is one of the most important subjects in the fields of computer vision and patternrecognition, and range image segmentation is the key of the analysis. This paper presents a range image segmentation technique based on RHT (Randomized Hough Transform). The proposed technique has the advantage of insensitivity to noise. Experiments were performed in a popular range image database (ABW) and compared to four other traditional range image segmentation algorithms on the same database, the results show the segmentation performance is superior to the above four algorithms.
Existing color constancy methods cannot handle both uniform colored surfaces and highly textured surfaces in a single integrated framework. Statistics-based methods require many surface colors, and become error prone ...
详细信息
Existing color constancy methods cannot handle both uniform colored surfaces and highly textured surfaces in a single integrated framework. Statistics-based methods require many surface colors, and become error prone when there are only few surface colors. In contrast, dichromatic-based methods can successfully handle uniformly colored surfaces, but cannot be applied to highly textured surfaces since they require precise color segmentation. In this paper, we present a single integrated method to estimate illumination chromaticity from single/multi-colored surfaces. Unlike the existing dichromatic-based methods, the proposed method requires only rough highlight regions, without segmenting the colors inside them. We show that, by analyzing highlights, a direct correlation between illumination chromaticity and image chromaticity can be obtained. This correlation is-clearly described in "inverse-intensity chromaticity space", a new two-dimensional space we introduce. In addition, by utilizing the Hough transform and histogram analysis in this space, illumination chromaticity can be estimated robustly, even for a highly textured surface. Experimental results on real images show the effectiveness of the method.
In local feature-based face recognition systems, the topographical locations of feature extractors directly affect the discriminative power of a recognizer. Better recognition accuracy can be achieved by the determina...
详细信息
In local feature-based face recognition systems, the topographical locations of feature extractors directly affect the discriminative power of a recognizer. Better recognition accuracy can be achieved by the determination of the positions of salient image locations. Most of the facial feature selection algorithms in the literature work with two assumptions: one, that the importance of each feature is independent of the other features, and two, that the kernels should be located at fiducial points. Under these assumption, one can only get a sub-optimal solution. In this paper, we present a methodology that tries to overcome this problem by relaxing the two assumptions using a formalism of subset selection problem. We use a number of feature selection algorithms and a genetic algorithm. Comparative results on the FERET dataset confirm the viability of our approach.
Breast cancer is by far the most common cancer in females. Early detection of lumps in the breast is a key to the successful treatment of this possible fatal disease. Breast self-examination (BSE) is considered as one...
详细信息
ISBN:
(纸本)0780377893
Breast cancer is by far the most common cancer in females. Early detection of lumps in the breast is a key to the successful treatment of this possible fatal disease. Breast self-examination (BSE) is considered as one of the early detection methods that is non-invasive, simple and can be carried out by a woman privately and at any time. However, currently, fully interactive systems do not exist and women depend on their subjective feeling while performing BSE procedures. We aim to develop an intelligent interactive multimedia system incorporating patternrecognition and machine vision techniques, and provide real-time feedback and objective data to assist and guide women to perform BSE accurately. One of the important components of the BSE technique is that the entire breast area is examined, where breast tissue may be encountered, in order to detect all possible lumps. This paper presents two search strategies to delineate the entire breast area which represents the potential boundary for the motion of a hand. This will enable the provision for a woman performing BSE with interactive objective feedback about the area of coverage based on the automatic extraction of her personal and volumetric breast information.
The proceedings contain 99 papers. The topics discussed include: fast fragment assemblage using boundary line and surface matching;archaeological fragment reconstruction using curve-matching;profile-based pottery reco...
ISBN:
(纸本)0769519008
The proceedings contain 99 papers. The topics discussed include: fast fragment assemblage using boundary line and surface matching;archaeological fragment reconstruction using curve-matching;profile-based pottery reconstruction;accurately estimating sherd 3D surface geometry with application to pot reconstruction;application of structured illumination in nano-scale vision;noise adaptive channel smoothing of low-dose images;indirect symbolic correlation approach to unsegmented text recognition;background line detection with a stochastic model;estimating tracking sources and sinks;generic event detection in sports video using cinematic features;towards perceptual interface for visualization navigation of large data sets;coevolutionary computation for synthesis of recognition systems;mirror shape recovery from image curves and intrinsic parameters: rotationally symmetric and conic mirrors;parametric subpixel matchpoint recovery with uncertainty estimation: a statistical approach;and tracking random sets of vehicles in terrain.
The proceedings contain 99 papers. The topics discussed include: fast fragment assemblage using boundary line and surface matching;archaeological fragment reconstruction using curve-matching;profile-based pottery reco...
ISBN:
(纸本)0769519008
The proceedings contain 99 papers. The topics discussed include: fast fragment assemblage using boundary line and surface matching;archaeological fragment reconstruction using curve-matching;profile-based pottery reconstruction;accurately estimating sherd 3D surface geometry with application to pot reconstruction;application of structured illumination in nano-scale vision;noise adaptive channel smoothing of low-dose images;indirect symbolic correlation approach to unsegmented text recognition;background line detection with a stochastic model;estimating tracking sources and sinks;generic event detection in sports video using cinematic features;towards perceptual interface for visualization navigation of large data sets;coevolutionary computation for synthesis of recognition systems;mirror shape recovery from image curves and intrinsic parameters: rotationally symmetric and conic mirrors;parametric subpixel matchpoint recovery with uncertainty estimation: a statistical approach;and tracking random sets of vehicles in terrain.
暂无评论