检索结果-内蒙古大学图书馆

作者： Gass, Tobias Pishchulin, Leonid Dreuw, Philippe Ney, Hermann Computer Vision Laboratory ETH Zurich Switzerland Computer Vision and Multimodal Computing MPI Informatics Saarbruecken Germany Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany

ISBN: (纸本)9781424491407

In this work, we present novel warping algorithms for full 2D pixel-grid deformations for face recognition. Due to high variation in face appearance, face recognition is considered a very difficult task, especially if only a single reference image, for example a mug-shot, per face is available. Usually model-based approaches with additional training data are used to cope with several types of variation occurring in facial imaging. Image warping contrarily yields a distance measure which is invariant with regard to several types of variation. This allows for precise recognition even using only very few reference observations. Due to the computationally complex problem of optimal 2D warping, pseudo-2D warping-based approaches in the past represented strong approximations of the original problem, and were mainly successful on data with low variability or rectified images. We propose a novel 2D warping method which is globally optimal and makes no prior assumtions on the data variability besides two-dimensional smootheness constraints which both avoid local mirroring and gaps and significantly speed up the optimization. Furthermore, we show that occlusion handling is imperative to obtain smooth warpings in a variety of domains. We evaluate our novel algorithm on various well known databases, such as the AR-Face and CMU-PIE database, and provide a detailed comparison to existing warping approaches. We show that by using simple relative 2D constraints, strong local features and a kernel, which is robust w.r.t. occlusions, our computationally complex approaches outperform state-of-the-art results for recognizing faces under varying expressions, occlusions and poses. Most interestingly, we achieve higher accuracy using fewer training instances per class compared to methods learning a model of the 3D shape. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Freehand HDR imaging of moving scenes with simultaneous resolution enhancement

Freehand HDR imaging of moving scenes with simultaneous reso...

引用

32nd Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2011

作者： Zimmer, Henning Bruhn, Andrés Weickert, Joachim Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University Saarbrücken Germany Vision and Image Processing Group Cluster of Excellence Multimodal Computing and Interaction Saarland University Saarbrücken Germany

Despite their high popularity, common high dynamic range (HDR) methods are still limited in their practical applicability: They assume that the input images are perfectly aligned, which is often violated in practise. Our paper does not only free the user from this unrealistic limitation, but even turns the missing alignment into an advantage: By exploiting the multiple exposures, we can create a super-resolution image. The alignment step is performed by a modern energy-based optic flow approach that takes into account the varying exposure conditions. Moreover, it produces dense displacement fields with subpixel precision. As a consequence, our approach can handle arbitrary complex motion patterns, caused by severe camera shake and moving objects. Additionally, it benefits from several advantages over existing strategies: (i) It is robust under outliers (noise, occlusions, saturation problems) and allows for sharp discontinuities in the displacement field, (ii) The alignment step neither requires camera calibration nor knowledge of the exposure times. (Hi) It can be efficiently implemented on CPU and GPU architectures. After the alignment is performed, we use the obtained subpixel accurate displacement fields as input for an energy-based, joint super-resolution and HDR (SR-HDR) approach. It introduces robust data terms and anisotropic smoothness terms in the SR-HDR literature. Our experiments with challenging real world data demonstrate that these novelties are pivotal for the favourable performance of our approach. © 2010 The Author(s).

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework

A highly efficient GPU implementation for variational optic ...

引用

11th European Conference on computer vision, ECCV 2010

作者： Gwosdek, Pascal Zimmer, Henning Grewenig, Sven Bruhn, Andrés Weickert, Joachim Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University Saarbrücken 66041 Germany Vision and Image Processing Group Cluster of Excellence Multimodal Computing and Interaction Saarland University Saarbrücken 66123 Germany

ISBN: (纸本)9783642357398

The Euler-Lagrange (EL) framework is the most widely-used strategy for solving variational optic flow methods. We present the first approach that solves the EL equations of state-of-the-art methods on sequences with pixels in near-realtime on GPUs. This performance is achieved by combining two ideas: (i) We extend the recently proposed Fast Explicit Diffusion (FED) scheme to optic flow, and additionally embed it into a coarse-to-fine strategy. (ii) We parallelise our complete algorithm on a GPU, where a careful optimisation of global memory operations and an efficient use of on-chip memory guarantee a good performance. Applying our approach to the variational 'Complementary Optic Flow' method (Zimmer et al. (2009)), we obtain highly accurate flow fields in less than a second. This currently constitutes the fastest method in the top 10 of the widely used Middlebury benchmark. © 2012 Springer-Verlag.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Person recognition in personal photo collections

arXiv

引用

arXiv 2017年

作者： Oh, Seong Joon Benenson, Rodrigo Fritz, Mario Schiele, Bernt Computer Vision and Multimodal Computing Group Max Planck Institute for Informatics Saarbrücken Germany

People nowadays share large parts of their personal lives through social media. Being able to automatically recognise people in personal photos may greatly enhance user convenience by easing photo album organisation. For human identification task, however, traditional focus of computer vision has been face recognition and pedestrian re-identification. Person recognition in social media photos sets new challenges for computer vision, including non-cooperative subjects (e.g. backward viewpoints, unusual poses) and great changes in appearance. To tackle this problem, we build a simple person recognition framework that leverages convnet features from multiple image regions (head, body, etc.). We propose new recognition scenarios that focus on the time and appearance gap between training and testing samples. We present an in-depth analysis of the importance of different features according to time and viewpoint generalisability. In the process, we verify that our simple approach achieves the state of the art result on the PIPA [1] benchmark, arguably the largest social media based benchmark for person recognition to date with diverse poses, viewpoints, social groups, and events. Compared the conference version of the paper [2], this paper additionally presents (1) analysis of a face recogniser (DeepID2+ [3]), (2) new method naeil2 that combines the conference version method naeil and DeepID2+ to achieve state of the art results even compared to post-conference works, (3) discussion of related work since the conference version, (4) additional analysis including the head viewpoint-wise breakdown of performance, and (5) results on the open-world setup. Copyright © 2017, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Image warping for face recognition: From local optimality towards global optimization

Image warping for face recognition: From local optimality to...

引用

作者： Pishchulin, Leonid Gass, Tobias Dreuw, Philippe Ney, Hermann MPI for Informatics - Computer Vision and Multimodal Computing Group Campus E1 4 D-66123 Saarbrücken Germany ETH Zurich Computer Vision Lab. Sternwartstrasse 7 CH-8092 Zurich Switzerland RWTH Aachen - Department 6 Ahornstr. 55 D-52056 Aachen Germany

This paper systematically analyzes the strengths and weaknesses of existing image warping algorithms on the tasks of face recognition. Image warping is used to cope with local and global image variability and in general is an NP-complete problem. Although many approximations have recently been proposed, neither thorough comparison, nor systematic analysis of methods in a common scheme has been done so far. We follow the bottom-up approach and analyze the methods with increasing degree of image structure preserved during optimization. We evaluate the presented warping approaches on four challenging face recognition tasks in highly variable domains. Our findings indicate that preserving maximum dependencies between neighboring pixels by imposing strong geometrical constraints leads to the best recognition results while making optimization efficient. © 2011 Elsevier Ltd. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Less contact: heart-rate detection without even touching the user

Less contact: heart-rate detection without even touching the...

引用

International Symposium on Wearable computers

作者： F. Michahelles R. Wicki B. Schiele Perceptual Computing and Computer Vision Group ETH Zurich Switzerland Multimodal Interactive Systems Technical University of Darmstadt Germany

Heart-rate sensing is very important. Whereas there are different methods and commercial products available, they all have a common drawback: the user has to mount some piece of sensor to his body. This paper provides a case study on how micro-impulse radar (MIR) can be used to sense heart-rate in a contact-free manner. With a sequence of tests the robustness of radar to different placements and even distances from the subject is shown. Since MIR is also cheap and power-efficient this paper suggests heart-rate sensing through radar as a promising approach.

关键词： Heart rate detection Radar Heart rate computer vision Aging Medical services Ubiquitous computing Pervasive computing Wearable computers Wrist

来源：评论

学校读者我要写书评

暂无评论

Warp that smile on your face: Optimal and smooth deformations for face recognition

Warp that smile on your face: Optimal and smooth deformation...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Tobias Gass Leonid Pishchulin Philippe Dreuw Hermann Ney Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany Computer Vision Laboratory ETH Zurich Switzerland Computer Vision and Multimodal Computing MPI Informatics Saarbruecken Germany

关键词： Pixel Face Face recognition Optimization Databases Approximation methods Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

arXiv

引用

arXiv 2023年

作者： Veeramacheneni, Lokesh Wolter, Moritz Kuehne, Hildegard Gall, Juergen High-Performance Computing and Analytics Lab University of Bonn Bonn53115 Germany Multimodal Learning Group University of Bonn Bonn53115 Germany Computer Vision Group University of Bonn Bonn53115 Germany

Modern metrics for generative learning like Fréchet Inception Distance (FID) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fréchet Wavelet Distance (FWD) as a domain-agnostic metric based on Wavelet Packet Transform (Wp). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, along with preserving both spatial and textural aspects. Specifically, we use Wp to project generated and dataset images to packet coefficient space. Further, we compute Fréchet distance with the resultant coefficients to evaluate the quality of a generator. This metric is general-purpose and dataset-domain agnostic, as it does not rely on any pre-trained network while being more interpretable because of frequency band transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD is able to generalize and improve robustness to domain shift and various corruptions compared to other metrics. © 2023, CC BY.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Towards distributed awareness - an artifact based approach

Towards distributed awareness - an artifact based approach

引用

IEEE Workshop on Mobile computing Systems and Applications (WMCSA)

作者： F. Michahelles S. Antifakos A. Schmidt B. Schiele M. Beigl Perceptual Computing and Computer Vision ETH Zurich Switzerland Embedded Interaction Group University of Munich (LMU) Germany Multimodal Interactive Systems Technical University of Darmstadt Germany Telecooperation Office (TecO) University of Karlsruhe Germany

Perception is a central issue for many applications in ubiquitous computing. However, in current implementations, sensing and distributed perception is re-invented over and over again. Identifying commonalities and synthesizing a common model would be more effective both from an economic as well as scientific perspective. We have analyzed the properties of ubicomp perception systems and used their characteristics as a main input for the design of a perception model. We present a layered perception model, discriminating functionality on artifact, setting, and application level. On the artifact layer, data collection, perception, and recognition for the particular artifact is modelled and implemented. The setting layer deals with perception and recognition tasks for a tightly coupled group of artifacts. In the application layer, perception and application-specific recognition resides. The approach was evaluated by building applications, two of which are also reported in the paper. The wider applicability of the model was assessed by analyzing further applications and how they map onto the artifact-based approach.

关键词： Pervasive computing Ubiquitous computing computer vision Data mining Embedded computing Interactive systems Application software Energy consumption Delay computer architecture

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：