Color histogram is an important part of content-based image retrieval systems. It is a common understanding that histograms that adapt to images can represent their color distributions more efficiently than histograms...
详细信息
Color histogram is an important part of content-based image retrieval systems. It is a common understanding that histograms that adapt to images can represent their color distributions more efficiently than histograms with fixed binnings. However, among existing dissimilarity measures, only the Earth Mover's Distance can compare histograms with different binnings. This paper presents a detailed quantitative study of fixed and adaptive binnings and the corresponding dissimilarity measures. An efficient dissimilarity measure is proposed for comparing histograms with different binnings. Extensive test results show that adaptive binning and dissimilarity produce the best overall performance, in terms of good accuracy, small number of bins, no empty bin, and efficient computation, compared to existing fixed binning schemes and dissimilarity measures.
Learning-enhanced relevance feedback is one of the most promising and active research directions in recent year's content-based image retrieval. However, the existing approaches either require prior knowledge of t...
详细信息
Learning-enhanced relevance feedback is one of the most promising and active research directions in recent year's content-based image retrieval. However, the existing approaches either require prior knowledge of the data or consume high computation cost, making them less practical. To overcome these difficulties and motivated by the successful history of optimal adaptive filters, in this paper, we present a new approach to interactive image retrieval. Specifically we cast the image retrieval problem in the optimal filtering framework, which does not require prior knowledge of the data, supports incremental learning, is simple to implement and achieves better performance than the state-of-the-art approaches. To evaluate the effectiveness and robustness of the proposed approach, extensive experiments have been carded out on a large heterogeneous image collection with 17,000 images. We report promising results on a wide variety of queries.
The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resulting final texture is typically computed ...
详细信息
The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resulting final texture is typically computed as a linear combination of reference textures. This is, however, not the optimal means for reconstructing textures, since this does not model the anisotropy in the texture projection. Furthermore, the spatial image sampling may be quite variable within a foreshortened surface. This also has important implications for computer vision techniques that involve analysis by synthesis and the image-based rendering (IBR) technique of view-dependent texture mapping (VDTM). In this paper, starting with sampling theory we show how weights should be spatially distributed for optimal texture construction. The local weights take into consideration the effects of anisotropy and variable spatial image sampling. We also present experimental results to verify our analysis.
There is a gap in most of patternrecognition approaches between the low-level processing.and the high-level analysis. A recent approach (1) fills this gap for the problem of structural identification. It supports exe...
详细信息
ISBN:
(纸本)081944300X
There is a gap in most of patternrecognition approaches between the low-level processing.and the high-level analysis. A recent approach (1) fills this gap for the problem of structural identification. It supports execution of the low-level imageprocessing.routines under full control of an identification task. This paper extends the approach to cover as possible omissions of some object details during detection, as well as partial occlusions.
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to individual training images. This paper ...
详细信息
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to individual training images. This paper presents a method for combining multiple images of a 3D object into a single model representation. This provides for recognition of 3D objects from any viewpoint, the generalization of models to non-rigid changes, and improved robustness through the combination of features acquired under a range of imaging conditions. The decision of whether to cluster a training image into an existing view representation or to treat it as a new view is based on the geometric accuracy of the match to previous model views. A new probabilistic model is developed to reduce the false positive matches that would otherwise arise due to loosened geometric constraints on matching 3D and non-rigid models. A system has been developed based on these approaches that is able to robustly recognize 3D objects in cluttered natural images in sub-second times.
An imaging system with a single effective viewpoint is called a central projection system. The conventional perspective camera is an example of a central projection system. Systems using mirrors to enhance the field o...
详细信息
An imaging system with a single effective viewpoint is called a central projection system. The conventional perspective camera is an example of a central projection system. Systems using mirrors to enhance the field of view while keeping a unique center of projection are also examples of central projection systems. Perspective image formation can be described by a linear model with well known properties. In general central catadioptric imaging the mapping between points in the world and in the image is highly nonlinear. This paper establishes a general model for central catadioptric image formation made up of three functions: a linear function mapping the worm into an oriented projective plane, a non-linear transformation between two oriented projective planes, and a collineation in the plane. The model is used to study issues in the projection of lines. The equations and geometric properties of general catadioptric imaging of lines are derived. The application of the results in auto-calibration of central catadioptric systems and reconstruction are discussed. A method to calibrate the system using three line images is presented.
The dichromatic reflectance model introduced by Shafer predicts that the colour signals of most materials fall on a plane spanned by a vector due to the material and a vector that represents the scene illuminant. Sinc...
详细信息
The dichromatic reflectance model introduced by Shafer predicts that the colour signals of most materials fall on a plane spanned by a vector due to the material and a vector that represents the scene illuminant. Since the illuminant is in the span of all dichromatic planes, colour constancy can be achieved by finding the intersection of two or more planes. Unfortunately, this approach has proven to be hard to get to work in practice. First, segmentation needs to be carried out and second, the actual intersection computation is quite unstable: small changes in the orientation of a dichromatic plane can significantly alter the location of the intersection point. In this paper we propose to ameliorate the instability problem by regularising the intersection. Specifically we introduce a constraint on the colour of the illuminant. We show how the intersection problem in the context of convex and non-convex illuminant constraints, based on the distribution of common light sources, can be solved. This algorithm coupled with the simplest of segmentations results in good estimation results for a large set of real images. Estimation performance is significantly better than for the unconstrained algorithm.
We present a model-based approach to detecting and describing compositions of buildings with complex roof-tops. Previous approaches have dealt with either simpler models or models which lack geometric information. In ...
详细信息
We present a model-based approach to detecting and describing compositions of buildings with complex roof-tops. Previous approaches have dealt with either simpler models or models which lack geometric information. In spite of increasing model complexity, we maintain the computation affordable by effectively using multiple over-lapping images. We obtain rooftop hypotheses in 3-D by using 3-D lines and junctions generated from multiple images. image-derived unedited elevation data is used to assist feature matching, and to generate rough cues of the presence of 3-D structures. Experimental results are shown on complex buildings.
We suggest a tool to decompose 3D discrete objects into simpler parts. Decomposition is guided by object thickness and is based on region growing. Region growing starts from a set of seeds suitably identified in the i...
详细信息
We suggest a tool to decompose 3D discrete objects into simpler parts. Decomposition is guided by object thickness and is based on region growing. Region growing starts from a set of seeds suitably identified in the innermost regions of the object. Our tool originates a decomposition into nearly convex and elongated parts. The decomposition is not affected remarkably by object rotation and has a limited computational cost. Since different recent imaging techniques give easier and cheaper access to 3D images, it is likely to believe that voxel-based decomposition tools, like the one here introduced, are of interest for future applications.
In this paper, we propose a new approach for recovering 3D geometry from uncalibrated and unknown rotation angles of single axis motions. Unlike previous approaches, the computation of trifocal tensor is not required....
详细信息
In this paper, we propose a new approach for recovering 3D geometry from uncalibrated and unknown rotation angles of single axis motions. Unlike previous approaches, the computation of trifocal tensor is not required. The new approach is based on fitting a conic to the corresponding points in different images of the same space point. It is then shown that the essential geometry of single axis motion is encoded by a conic. Since we are determining only 5 parameters from N views instead of 18 parameters from a sub-sequence of 3 views, our approach is much more simple and robust. The experiments on a real image sequence demonstrate the accuracy and robustness of the new algorithm.
暂无评论