作者：
Kober, VCICESE
Div Fis Aplicada Dept Ciencias Computac Ensenada 22860 Baja California Mexico
Robust adaptive correlations based on rank order operations such as alpha-trimmed sum and median for illumination-invariant patternrecognition are proposed. Several properties of the correlations are investigated. Th...
详细信息
ISBN:
(纸本)0819450766
Robust adaptive correlations based on rank order operations such as alpha-trimmed sum and median for illumination-invariant patternrecognition are proposed. Several properties of the correlations are investigated. Their performance for detection of noisy objects is compared to the conventional linear correlation in terms of noise robustness and discrimination capability. computer simulation results for a test image corrupted by mixed additive and impulsive noise are provided and discussed.
In this paper, we propose a novel and efficient approach for active unsurpervised texture segmentation. First, we show how we can extract a small set of good features for texture segmentation based on the structure te...
详细信息
In this paper, we propose a novel and efficient approach for active unsurpervised texture segmentation. First, we show how we can extract a small set of good features for texture segmentation based on the structure tensor and nonlinear diffusion. Then, we propose a variational framework that incorporates these features in a level set based unsupervised segmentation that adaptively takes into account their estimated statistical information inside and outside the region to segment. The approach has been tested on various textured images, and its performance is favorably compared to recent studies.
We present a novel algorithm to reconstruct the geometry and photometry of a scene with occlusions from a collection of defocused images. The presence of a finite lens aperture allows us to recover portions of the sce...
详细信息
We present a novel algorithm to reconstruct the geometry and photometry of a scene with occlusions from a collection of defocused images. The presence of a finite lens aperture allows us to recover portions of the scene that would be occluded in a pin-hole projection, thus "uncovering" the occlusion. We estimate the shape of each object (a surface, including the occluding boundaries), and its radiance (a positive function defined on the surface, including portions that are occluded by other objects).
We present a novel algorithm for optimally segmenting dynamic scenes containing multiple rigidly moving objects. We cast the motion segmentation problem as a constrained nonlinear least squares problem which minimizes...
详细信息
We present a novel algorithm for optimally segmenting dynamic scenes containing multiple rigidly moving objects. We cast the motion segmentation problem as a constrained nonlinear least squares problem which minimizes the reprojection error subject to all multibody epipolar constraints. By converting this constrained problem into an unconstrained one, we obtain an objective function that depends on the motion parameters only (fundamental matrices), but is independent on the segmentation of the image features. Therefore, our algorithm does not iterate between feature segmentation and single body motion estimation. Instead, it uses standard nonlinear optimization techniques to simultaneously recover all the fundamental matrices, without prior segmentation. We test our approach on a real sequence.
This paper studies the problem of combining region and boundary cues for natural image segmentation. We employ a large database of manually segmented images in order to learn an optimal affinity function between pairs...
详细信息
This paper studies the problem of combining region and boundary cues for natural image segmentation. We employ a large database of manually segmented images in order to learn an optimal affinity function between pairs of pixels. These pairwise affinities can then be used to cluster the pixels into visually coherent groups. Region cues are computed as the similarity in brightness, color, and texture between image patches. Boundary cues are incorporated by looking for the presence of an "intervening contour", a large gradient along a straight line connecting two pixels. We first use the dataset of human segmentations to individually optimize parameters of the patch and gradient features for brightness, color, and texture cues. We then quantitatively measure the power of different feature combinations by computing the precision and recall of classifiers trained using those features. The mutual information between the output of the classifiers and the same-segment indicator function provides an alternative evaluation technique that yields identical conclusions. As expected, the best classifier makes use of brightness, color, and texture features, in both patch and gradient forms. We find that for brightness, the gradient cue outperforms the patch similarity. In contrast, using color patch similarity yields better results than using color gradients. Texture is the most powerful of the three channels, with both patches and gradients carrying significant independent information. Interestingly, the proximity of the two pixels does not add any information beyond that provided by the similarity cues. We also find that the convexity assumptions made by the intervening contour approach are supported by the ecological statistics of the dataset.
Relevance feedback has been an indispensable component for multimedia retrieval systems. In this paper, we present an adaptive pattern discovery method, which addresses relevance feedback by interactively discovering ...
详细信息
Relevance feedback has been an indispensable component for multimedia retrieval systems. In this paper, we present an adaptive pattern discovery method, which addresses relevance feedback by interactively discovering meaningful patterns of relevant objects. To facilitate pattern discovery, we first present a dynamic feature extraction method, which aims to alleviate the curse of dimensionality by extracting a feature subspace using balanced information gain. In the feature subspace, we train an online pattern classification method called adaptive random forests to classify multimedia objects as relevant or irrelevant. Our adaptive random forests adapts the traditional classification method known as random forests for relevance feedback. It improves the efficiency of pattern discovery by choosing the most-informative samples for online learning. Extensive experiments are carried out on a Corel image set (with 31,438 images) to evaluate the performance of our method as compared against the state-of-the-art approaches.
We develop a fast and accurate variable window approach. The two main ideas for achieving accuracy are choosing a useful range of window sizes/shapes for evaluation and developing a new window cost which is particular...
详细信息
ISBN:
(纸本)0769519008
We develop a fast and accurate variable window approach. The two main ideas for achieving accuracy are choosing a useful range of window sizes/shapes for evaluation and developing a new window cost which is particularly suitable for comparing windows of different sizes. The speed of our approach is due to the Integral image technique, which allows computation of our window cost over any rectangular window in constant time, regardless of window size. Our method ranks in the top four on the Middlebury stereo database with ground truth, and performs best out of methods which have comparable efficiency.
Man made indoors environments posses regularities which can be efficiently exploited in automated model acquisition by means of visual sensing. In this context we propose an approach for inferring a topological model ...
详细信息
Man made indoors environments posses regularities which can be efficiently exploited in automated model acquisition by means of visual sensing. In this context we propose an approach for inferring a topological model of an environment from images or the video stream captured by a mobile robot during exploration. The proposed model consists of a set of locations and neighbourhood relationships between them. Initially each location in the model is represented by a collection of similar, temporally adjacent views, with the similarity defined according to a simple appearance based distance measure. The sparser representation is obtained in a subsequent learning stage by means of Learning Vector Quantization (LVQ). The quality of the model is tested in the context of qualitative localization scheme by means of location recognition: given a new view, the most likely location where that view came from is determined.
Appearance models yield a compact representation of shape, pose and illumination variations. The probabilistic appearance model, introduced by Moghaddam et al. (proceedings of the International conference on computer ...
详细信息
Appearance models yield a compact representation of shape, pose and illumination variations. The probabilistic appearance model, introduced by Moghaddam et al. (proceedings of the International conference on computer Vision, Cambridge, MA, June 1995, p. 687;ieee Trans. pattern Anal. Mach. Intell. 19 (7) (1997) 696) has recently shown excellent performances in pattern detection and recognition, outperforming most other linear and non-linear approaches. Unfortunately, the complexity of this model remains high. In this paper, we introduce an efficient approximation of this model, which enables fast implementations in statistical estimation-based schemes. Gains in complexity and cpu time of more than 10 have been obtained, without any loss in the quality of the results. (C) 2002 patternrecognitionsociety. Published by Elsevier Science Ltd. All rights reserved.
Optical Music recognition (OMR) is the automatic recognition of a scanned page of printed music notation by computer. A new approach to this patternrecognition problem is presented in this paper. The concept of direc...
详细信息
ISBN:
(纸本)0780377028
Optical Music recognition (OMR) is the automatic recognition of a scanned page of printed music notation by computer. A new approach to this patternrecognition problem is presented in this paper. The concept of direction number has been defined according to the musical notation's statistic and structural characteristic, and then make use of mathematical morphology theory to process musical score image and recognize musical information. Specialized algorithms are used firstly to preprocess a musical score image and then recognize stafflines, barlines, pitch, note values, clef, etc.. Finally the musical information of the musical score image is stored in the MIDI format. Making use of our proposed algorithms, which can process multiple staves per system and oblique musical score, an OMR prototype system has been developed and designed. At last, about 50 musical score image which are downloaded from the websites have been used to demonstrate the efficiency and accuracy of the system.
暂无评论