检索结果-内蒙古大学图书馆

conference on computer vision and pattern recognition (CVPR)

作者： G. Sundaramoorthi J.D. Jackson A. Yezzi A.C. Mennucci School of Electrical and Computer Engineering Georgia Institute of Technology USA Scuola Normale Superiore Italy

Recently proposed Sobolev active contours introduced a new paradigm for minimizing energies defined on curves by changing the traditional cost of perturbing a curve and thereby redefining their gradients. Sobolev active contours evolve more globally and are less attracted to certain intermediate local minima than traditional active contours. In this paper we analyze Sobolev active contours in the Fourier domain in order to understand their evolution across different scales. This analysis shows an important and useful behavior of Sobolev contours, namely, that they move successively from coarse to increasingly finer scale motions in a continuous manner. Along with other properties, the previous observation reveals that Sobolev active contours are ideally suited for tracking problems that use active contours. Our purpose in this work is to show how a variety of active contour based tracking methods can be significantly improved merely by evolving the active contours according to the Sobolev method.

关键词： Active contours Shape Costs Motion analysis Video sequences Image edge detection Robustness Deformable models

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Patch Tensor for Facial Expression Hallucination

Multi-Resolution Patch Tensor for Facial Expression Hallucin...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Kui Jia Shaogang Gong Department of Computer Science Queen''s Mary University of London UK

In this paper, we propose a sequential approach to hallucinate/ synthesize high-resolution images of multiple facial expressions. We propose an idea of multi-resolution tensor for super-resolution, and decompose facial expression images into small local patches. We build a multi-resolution patch tensor across different facial expressions. By unifying the identity parameters and learning the subspace mappings across different resolutions and expressions, we simplify the facial expression hallucination as a problem of parameter recovery in a patch tensor space. We further add a high-frequency component residue using nonparametric patch learning from high-resolution training data. We integrate the sequential statistical modelling into a Bayesian framework, so that given any low-resolution facial image of a single expression, we are able to synthesize multiple facial expression images in high-resolution. We show promising experimental results from both facial expression database and live video sequences.

关键词： Tensile stress Image resolution Training data Bayesian methods Image databases Video sequences Robustness Active appearance model Cameras Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

Fast Human Detection Using a Cascade of Histograms of Orient...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Qiang Zhu Mei-Chen Yeh Kwang-Ting Cheng S. Avidan Electrical & Computer Engineering Department University of California Santa Barbara CA USA Mitsubishi Electric Research Laboratories Inc. Cambridge MA USA

We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. The features used in our system are HoGs of variable-size blocks that capture salient features of humans automatically. Using AdaBoost for feature selection, we identify the appropriate set of blocks, from a large set of possible blocks. In our system, we use the integral image representation and a rejection cascade which significantly speed up the computation. For a 320 × 280 image, the system can process 5 to 30 frames per second depending on the density in which we scan the image, while maintaining an accuracy level similar to existing methods.

关键词： Humans Histograms Face detection Support vector machines Support vector machine classification Assembly Laboratories Image representation Object detection Clothing

来源：评论

学校读者我要写书评

暂无评论

computer vision Algorithms for Quantifying the Growth and Behavior of Neurons Cultured on Nanofabricated Surfaces

Computer Vision Algorithms for Quantifying the Growth and Be...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Muhammad-Amri Abdul Karim Khalid Al-Kofahi Badrinath Roysam Natalie Dowell-Mesfin Rifat J. Hussain William Shain James N. Turner Electrical Computer & Systems Engineering Dept. Rensselaer Polytechnic Institute Troy NY Electrical Computer & Systems Engineering Dept. Rensselaer Polytechnic Institute Troy NY USA The Wadsworth Center Department of Health Albany NY The Wadsworth Center Department of Health Albany NY USA

Neuron growth on nanofabricated silicon surfaces, once understood, is fundamental to engineer circuits involving neurons and electronic components, leading to applications such as next-generation brain implants, and high-throughput neurologic drug screening assay systems. Precise quantification of neuronal growth and behavior from image samples requires computer vision algorithms for automatic tracing of neurons, and flexible algorithms for reliable registration and analysis of multi-fluorophore imagery. The tracing algorithms must be robust to high levels of clutter and common imaging artifacts, process discontinuities, and quantum noise, especially when live neurons are imaged. Finally, the large numbers of images that must be processed for a hypothesis test or assay call for computationally efficient algorithms. A fully automated neuron tracing algorithm based on the use of robust detection and estimation principles is described here that meets the above needs. It takes 2 seconds to trace and extract morphological statistics from a typical 1280 × 1024 image on a Pentium III, 1 GHz personal computer. It was validated against manually generated traces and the errors were in the range of 1-5% per image.

关键词： Neurons Surface topography Algorithm design and analysis Robustness computer vision Surface morphology Nerve fibers

来源：评论

学校读者我要写书评

暂无评论

A Simple Bayesian Framework for Content-Based Image Retrieval

A Simple Bayesian Framework for Content-Based Image Retrieva...

引用

conference on computer vision and pattern recognition (CVPR)

作者： K.A. Heller Z. Ghahramani Gatsby Computational Neuroscience Unit University College London UK Machine Learning Department Carnegie Mellon University Pittsburgh PA USA Department of Engineering University of Cambridge UK

We present a Bayesian framework for content-based image retrieval which models the distribution of color and texture features within sets of related images. Given a userspecified text query (e.g. "penguins") the system first extracts a set of images, from a labelled corpus, corresponding to that query. The distribution over features of these images is used to compute a Bayesian score for each image in a large unlabelled corpus. Unlabelled images are then ranked using this score and the top images are returned. Although the Bayesian score is based on computing marginal likelihoods, which integrate over model parameters, in the case of sparse binary data the score reduces to a single matrix-vector multiplication and is therefore extremely efficient to compute. We show that our method works surprisingly well despite its simplicity and the fact that no relevance feedback is used. We compare different choices of features, and evaluate our results using human subjects.

关键词： Bayesian methods Image retrieval Content based retrieval Distributed computing Sparse matrices Image databases Histograms Gabor filters computer vision Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Shape Guided Object Segmentation

Shape Guided Object Segmentation

引用

conference on computer vision and pattern recognition (CVPR)

作者： E. Borenstein J. Malik Division of Applied Mathematics Brown University USA Department of Electrical Engineering and Computer Science University of California Berkeley USA

We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.

关键词： Shape Object segmentation Image segmentation Bayesian methods Object detection Approximation algorithms Inference algorithms Horses Robustness Labeling

来源：评论

学校读者我要写书评

暂无评论

Three Dimensional Short-term Memory Image

Three Dimensional Short-term Memory Image

引用

International conference on pattern recognition

作者： S. Morita Faculty of Engineering Yamaguchi University Japan

We proposed the three dimensional short-term memory image related to human memory and human vision. Three dimensional short-term memory image composed of the three dimensional features reconstructed from the binocular foveated vision. The next fixation point is determined statistically from the feature points in the image projected from the 3D short-term memory image. We show the effectiveness by simulating the binocular eye movements for the virtual world generated computer graphics and for the real world using pan-tilt cameras. It is found that the viewing world does not change suddenly though the eye moves quickly by introducing the 3D short-term memory

关键词： Humans Retina Image reconstruction Robot vision systems computer vision Psychology Eyes Computational modeling computer simulation computer graphics

来源：评论

学校读者我要写书评

暂无评论

Landmark-Based Geodesic Computation for Heuristically Driven Path Planning

Landmark-Based Geodesic Computation for Heuristically Driven...

引用

conference on computer vision and pattern recognition (CVPR)

作者： G. Peyre L.D. Cohen CMAP UMR CNRS 7641 École Polytechnique Palaiseau France CEREMADE UMR CNRS 7534 Université Paris Dauphine Paris France

This paper presents a new method to quickly extract geodesic paths on images and 3D meshes. We use a heuristic to drive the front propagation procedure of the classical Fast Marching. This results in a modification of the Fast Marching algorithm that is similar to the A algorithm used in artificial intelligence. In order to find very quickly geodesic paths between any given couples of points, we advocate for the initial computation of distance maps to a set of landmark points and make use of these distance maps through a relevant heuristic. We show that our method brings a large speed up for large scale applications that require the extraction of geodesics on images and 3D meshes. We introduce two distortion metrics in order to find an optimal seeding of landmark points for the targeted applications. We also propose a compression scheme to reduce the memory requirement without impacting the quality of the extracted paths.

关键词： Geophysics computing Path planning computer vision Artificial intelligence Application software Data mining Euclidean distance Large-scale systems Image coding Graph theory

来源：评论

学校读者我要写书评

暂无评论

Scene matching using F-histogram-based features with possibilistic C-means optimization

引用

FUZZY SETS AND SYSTEMS 2007年第3期158卷 253-269页

作者： Sjahputera, Ozy Keller, James A. Univ Missouri Dept Pathol & Anatom Sci Columbia MO 65212 USA Univ Missouri Dept Elect & Comp Engn Columbia MO 65211 USA

This paper outlines further advances from initial findings previously reported in [O. Sjahputera, J.M. Keller, Possibilistic C-means in scene matching, Fourth Internal. Conf. of the European Society for Fuzzy Logic and Technology (EUSFLAT), 2005, pp. 669-675]. We propose a scene matching approach based on spatial relationships among objects in the images to determine if two images acquired under different viewing conditions capture the same scene. This is a difficult problem in computer vision. Our approach produces a mapping of objects from one view to the other, and recovers the viewing transformation parameters. The core of the system relies on capturing spatial relationship information through Force Histograms as affine-invariant image descriptors. Object mapping across images is performed by finding the best correspondence map (FMAP) between force histograms in the two images. The major problem is that the number of potential FMAPs is large, even for modest numbers of scene objects. Hence, search optimization is required. The correct FMAP contains histogram correspondences represented by similar feature vectors. Therefore, dense regions in the feature space are suspected to contain these vectors. Possibilistic C-means (PCM) clustering is used to find these dense regions. The centroids of these dense regions are used to generate the FMAPs. Previously, the FMAP was generated using a nearest-neighbor like approach. In this study, we propose an improved version of this method by incorporating fuzzy memberships into the FMAP building process. Here, the fitness of FMAP candidates are assessed with respect to all histogram correspondences already in FMAP, not just from an initial seed point alone. The best FMAP is selected and translated into a mapping scheme that connects the objects in the two images. (c) 2006 Elsevier B.V. All rights reserved.

关键词： scene matching spatial relations force histograms possibilistic C-means pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Sparse and Semi-supervised Visual Mapping with the S^3GP

Sparse and Semi-supervised Visual Mapping with the S^3GP

引用

conference on computer vision and pattern recognition (CVPR)

作者： O. Williams A. Blake R. Cipolla University of Cambridge UK Microsoft Research UK Limited University of Cambridge Cambridgeshire UK

This paper is about mapping images to continuous output spaces using powerful Bayesian learning techniques. A sparse, semi-supervised Gaussian process regression model (S3GP) is introduced which learns a mapping using only partially labelled training data. We show that sparsity bestows efficiency on the S3GP which requires minimal CPU utilization for real-time operation; the predictions of uncertainty made by the S3GP are more accurate than those of other models leading to considerable performance improvements when combined with a probabilistic filter; and the ability to learn from semi-supervised data simplifies the process of collecting training data. The S3GP uses a mixture of different image features: this is also shown to improve the accuracy and consistency of the mapping. A major application of this work is its use as a gaze tracking system in which images of a human eye are mapped to screen coordinates: in this capacity our approach is efficient, accurate and versatile.

关键词： Training data Gaussian processes Uncertainty Robustness computer vision Bayesian methods Predictive models Filters Humans Runtime

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：