This paper presents a new approach to ranking relevant images for retrieval. Distance in the feature space associated with a kernel is used to rank relevant images. An adaptive quasiconformal mapping based on relevanc...
详细信息
This paper presents a new approach to ranking relevant images for retrieval. Distance in the feature space associated with a kernel is used to rank relevant images. An adaptive quasiconformal mapping based on relevance feedback is used to generate successive new kernels. The effect of the quasiconformal mapping is a change in the spatial resolution of the feature space. The spatial resolution around irrelevant samples is dilated, whereas the spatial resolution around relevant samples is contracted. This new space created by the quasiconformal kernel is used to measure the distance between the query and the images in the database. An interesting interpretation of the metric is found by looking at the Taylor series approximation to the original kernel Then the squared distance in the feature space can be seen as a combination of a parzen window estimate of the squared Chi-squared distance and a weighted squared Euclidean distance. Experimental results using real-world data validate the efficacy of our method.
In this paper, we study face hallucination or synthesizing a high-resolution face image from a low-resolution input, with the help of a large collection of other high-resolution face images. We develop a two-step stat...
详细信息
In this paper, we study face hallucination or synthesizing a high-resolution face image from a low-resolution input, with the help of a large collection of other high-resolution face images. We develop a two-step statistical modeling approach that integrates both a global parametric model and a local nonparametric model. First, we derive a global linear model to learn the relationship between the high-resolution face images and their smoothed and down-sampled lower resolution ones. Second, the residual between an original high-resolution image and the reconstructed high-resolution image by learned linear model is modeled by a patch-based nonparametric Markov network, to capture the high-frequency content of faces. By integrating both global and local models, we can generate photo-realistic face images. Our approach is demonstrated by extensive experiments with high-quality hallucinated faces.
We propose a model-based curve evolution technique for segmentation of images containing known object types. In particular, motivated by the work of Leventon, Grimson, and Faugeras, we derive a parametric model for an...
详细信息
We propose a model-based curve evolution technique for segmentation of images containing known object types. In particular, motivated by the work of Leventon, Grimson, and Faugeras, we derive a parametric model for an implicit representation of the segmenting curve by applying principal component analysis to a collection of signed distance representations of the training data. The parameters of this representation are then calculated to minimize an objective function for segmentation. We found the resulting algorithm to be computationally efficient, able to handle multidimensional data, robust to noise and initial contour placements, while at the same time, avoiding the need for point correspondences during the training phase of the algorithm. We demonstrate this technique by applying it to two medical applications.
We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time course...
详细信息
We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. Att implementation of this approach is developed for an appearance model based on the filter responses front a steerable pyramid. This model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions or variations in 3D pose. We show experimental results on a variety of natural image sequences of people moving within cluttered environments.
It is often difficult to come up with a well-principled approach to the selection of a spatial indexing mechanism for medical image databases. Spatial information about lesions in medical images is critically importan...
详细信息
It is often difficult to come up with a well-principled approach to the selection of a spatial indexing mechanism for medical image databases. Spatial information about lesions in medical images is critically important in disease diagnosis and plays an important role in image retrieval. Unfortunately, the images are rarely indexed properly for clinically useful retrieval. One example is the well-known R-tree and its variants which index image objects based on their physical locations in an "absolute" way. However, such information is not meaningful in medical content-based image retrieval systems, and the approaches above suffer from problems caused by variations in object size and shape, imprecise image centering, etc. A more appropriate approach, which does not require object registration, is to model the spatial relationships between the lesions and anatomical landmarks. To convey diagnostic information, lesions must exist in certain locations with regard to the landmarks. In this paper, we show that the histogram of forces (which represents the relative position between two objects) provides an efficient spatial indexing mechanism in the medical domain.
This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element. Our approac...
详细信息
This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element. Our approach models both the foreground and background color distributions with spatially-varying sets of Gaussians, and assumes a fractional blending of the foreground and background colors to produce the final output. It then uses a maximum-likelihood criterion to estimate the optimal opacity foreground and background simultaneously. In addition to providing a principled approach to the matting problem, our algorithm effectively handles objects with intricate boundaries, such as hair strands and fur, and provides an improvement over existing techniques for these difficult cases.
A major problem with interactive displays based on front-projection is that users cast undesirable shadows on the display surface. This situation is only partially-addressed by mounting a single projector at an extrem...
详细信息
A major problem with interactive displays based on front-projection is that users cast undesirable shadows on the display surface. This situation is only partially-addressed by mounting a single projector at an extreme angle and prewarping the projected image to undo keystoning distortions. This paper demonstrates that shadows can be muted by redundantly-illuminating the display surface using multiple projectors, all mounted at different locations. However, this technique alone does not eliminate shadows: multiple projectors create multiple dark regions on the surface (penumbral occlusions). We solve the problem by using cameras to automatically identify occlusions as they occur and dynamically adjust each projector's output so that additional light is projected onto each partially-occluded patch. The system is self-calibrating: relevant homographies relating projectors, cameras and the display surface are recovered by observing the distortions induced in projected calibration patterns. The resulting redundantly-projected display retains the high image quality of a single-projector system while dynamically correcting for all penumbral occlusions. Our initial two-projector implementation operates at 3 Hz.
A goal of image-based rendering is to synthesize as realistically as possible man made and natural objects. This paper presents a method for image-based modeling and rendering of objects with arbitrary (possibly aniso...
详细信息
A goal of image-based rendering is to synthesize as realistically as possible man made and natural objects. This paper presents a method for image-based modeling and rendering of objects with arbitrary (possibly anisotropic and spatially varying) BRDFs. An object is modeled by sampling the surface's incident light field to reconstruct a non-parametric apparent BRDF at each visible point on the surface. This can be used to render the object from the same viewpoint but under arbitrarily specified illumination. We demonstrate how these object models can be embedded in synthetic scenes and rendered under global illumination which captures the interreflections between real and synthetic objects. We also show how these image-based models can be automatically composited onto video footage with dynamic illumination so that the effects (shadows and shading) of the lighting on the composited object match those of the scene.
Pixels in an area image sensor are normally arranged in a regular matrix, because this is the best way for sensor layout, display and imageprocessing.image sensors in CMOS aps technologies offer great flexibility in...
详细信息
ISBN:
(纸本)0819439843
Pixels in an area image sensor are normally arranged in a regular matrix, because this is the best way for sensor layout, display and imageprocessing.image sensors in CMOS aps technologies offer great flexibility in the design. Nearly any shape for the light-sensitive fotodiode and any arrangements are possible. But one disadvantage of CMOS aps;(active pixel sensor) is, that they need some space in the sensitive area for the electronic pixel circuitry. We developed and investigated a CMOS sensor with a chessboard like pixel pattern, where the white fields are the sensitive fotodiodes and the black fields are for electronic circuitry. The black fields must be interpolated for displaying. So we get an image with a double number of pixels, which is again a regular matrix of pixels which can be displayed on a monitor and is suited for standard imageprocessing. We compared such a chess-pattern sensor with regular matrix image sensors. For this we made some computer simulations of these variations regarding the number of pixels and the optical fill factor. The performance of the images is evaluated concerning technical data, like line-resolution, SFR, artefacts and the visual impression as well. We show simulations with real images of the same scene: Two simulations are with a normal regular pixel arrangement and the other with a sensor having a chesspattern pixel arrangement. Sensor with chess-pattern pixel arrangement can be used in video-, industrial- and still picture-cameras for black and white and color imaging. It will result in an improved image quality compared to regular matrix sensors.
We address the problem of finding a set of contour curves in a 2D or 3D image. We consider the problem of perceptual grouping and contour completion, where the data is an unstructured set of regions in the image. A ne...
详细信息
We address the problem of finding a set of contour curves in a 2D or 3D image. We consider the problem of perceptual grouping and contour completion, where the data is an unstructured set of regions in the image. A new method to find complete curves from a set of edge points is presented. Contours are found as minimal paths between connected components, using the fast marching algorithm. We find the minimal paths between each of these components, until the complete set of these "regions" is connected. The paths are obtained using backpropagation from the saddle points to both components. We then extend this technique to 3D. The data is a set of connected components in a 3D image. We find 3D minimal paths that link together these components. Using a potential based on vessel detection, we illustrate the capability of our approach to reconstruct tree structures in a 3D medical image dataset.
暂无评论