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

Combining the advantages of local and global optic flow methods

Combining the advantages of local and global optic flow meth...

引用

24th Symposium of the German pattern recognition Association, DAGM 2002

作者： Bruhn, Andres Weickert, Joachim Schnorr, Christoph Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University 66041 Saarbrücken Germany Computer Vision Graphics and Pattern Recognition Group Department of Mathematics and Computer Science University of Mannheim 68131 Mannheim Germany

ISBN: (纸本)354044209X

Differential methods are frequently used techniques for optic flow computations. They can be classified into local methods such as the Lucas-Kanade technique or Bigün's structure tensor method, and into global methods such as the Horn-Schunck approach and its modifications. Local methods are known to be more robust under noise, while global techniques yield 100% dense flow fields. No clear attempts to combine the advantages of these two classes of methods have been made in the literature so far. This problem is addressed in our paper. First we juxtapose the role of smoothing processes that are required in local and global differential methods for optic flow computation. This discussion motivates us to introduce and evaluate a novel method that combines the advantages of local and global approaches: It yields dense flow fields that are robust against noise. Finally experiments with different sequences are performed demonstrating its excellent results. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Flow fields

来源：评论

学校读者我要写书评

暂无评论

Mash up of breaking news and contextual web information: A novel service for connected television

Mash up of breaking news and contextual web information: A n...

引用

2010 19th International Conference on computer Communications and Networks, ICCCN 2010

作者： Chattopadhyay, T. Pal, Arpan Garain, Utpal Innovation Lab. Kolkata Tata Consultancy Services Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781424471164

The Connected TV can be described as an Internet enabled TV. In the current paper we have proposed a system for connected TV that mash up the information from internet and RSS feeds related to the breaking news aired over the TV. The proposed system initially localize the text regions from the streamed video in hybrid mode, then recognize them and spot the key words and finally fetch the related information from Internet. Our experimental results show that the localization of the text regions from the video can work with no misses but have some false positives which are taken care by data semantic analysis. The errors of the Optical Character recognition (OCR) module are taken care by using string comparing techniques like longest common subsequence matching and Leveinsthein distance while matching with the RSS feed or internet. © 2010 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of gothic and baroque architectural elements

Classification of gothic and baroque architectural elements

引用

2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012

作者： Shalunts, Gayane Haxhimusa, Yll Sablatnig, Robert Institute of Computer Aided Automation Computer Vision Lab. Vienna University of Technology Austria Institute of Computer Graphics and Algorithms Pattern Recognition and Image Processing Lab. Vienna University of Technology Austria

ISBN: (纸本)9783200023284

Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectural styles is viewed as a task of classifying separate architectural structural elements. In the scope of building facade architectural style classification the current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade. Since certain gradient directions dominate on the shape of each architectural element, discrimination between dominating gradients means classification of architectural elements and thus architectural styles. We use local features to describe gradient directions. Our approach is based on clustering and learning of local features and yields a high classification rate. © 2012 Institute of Telecommunica.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation From Single Image And Semantic Prior

Depth Estimation From Single Image And Semantic Prior

引用

IEEE International Conference on Image Processing

作者： Praful Hambarde Akshay Dudhane Prashant W. Patil Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab IIT Ropar

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

The multi-modality sensor fusion technique is an active research area in scene understating. In this work, we explore the RGB image and semantic-map fusion methods for depth estimation. The LiDARs, Kinect, and TOF depth sensors are unable to predict the depth-map at illuminate and monotonous pattern surface. In this paper, we propose a semantic-to-depth generative adversarial network (S2D-GAN) for depth estimation from RGB image and its semantic-map. In the first stage, the proposed S2D-GAN estimates the coarse level depthmap using a semantic-to-coarse-depth generative adversarial network (S2CD-GAN) while the second stage estimates the fine-level depth-map using a cascaded multi-scale spatial pooling network. The experimental analysis of the proposed S2D-GAN performed on NYU-Depth-V2 dataset shows that the proposed S2D-GAN gives outstanding result over existing single image depth estimation and RGB with sparse samples methods. The proposed S2D-GAN also gives efficient results on the real-world indoor and outdoor image depth estimation.

关键词： Estimation Semantics Generators Robot sensing systems Laser radar Generative adversarial networks Training

来源：评论

学校读者我要写书评

暂无评论

Texton-based fabric defect detection and recognition

引用

Iranian Journal of Electrical and computer Engineering 2011年第2期10卷 57-69页

作者： Behravan, M. Tajeripour, F. Azimifar, Z. Boostani, R. Computer Vision and Pattern Recognition Group School of Electrical and Computer Engineering Shiraz University Shiraz Iran

Automatic fabric defect classification is an essential stage in production line of textile manufactures. Here, a novel method for simultaneous detection and classification of fabric defects is presented. Each fabric defect type produces a locally specific type of texture. In this paper for the first time textons are used to describe local structure of fabric defects textures. In the method, an image is divided into several blocks in which features based on filter banks are extracted from them. According to these features, the algorithm determines defective windows and their defect types. The employed datasets in this study contain six types of well-known defects of patterned fabrics and four types of unpatterned fabric defects. Our experiments have yielded excellent results and this shows that descriptors based on texture properties of defective regions are suitable for classification task. The proposed method leads to improved and robust detection and classification results compared to the traditional methods. © 2011 ACECR.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A survey of historical document image datasets

A survey of historical document image datasets

引用

作者： Nikolaidou, Konstantina Seuret, Mathias Mokayed, Hamam Liwicki, Marcus EISLAB Machine Learning Group Luleå University of Technology Aurorum 1 Norrbotten Luleå97187 Sweden Pattern Recognition Lab Computer Vision Group Friedrich-Alexander-Universität Martensstr. 3 Bavaria Erlangen91058 Germany

This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten manuscripts and early prints. Finding appropriate datasets for historical document analysis is a crucial prerequisite to facilitate research using different machine learning algorithms. However, because of the very large variety of the actual data (e.g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task. This work fills this gap, presenting a meta-study on existing datasets. After a systematic selection process (according to PRISMA guidelines), we select 65 studies that are chosen based on different factors, such as the year of publication, number of methods implemented in the article, reliability of the chosen algorithms, dataset size, and journal outlet. We summarize each study by assigning it to one of three pre-defined tasks: document classification, layout structure, or content analysis. We present the statistics, document type, language, tasks, input visual aspects, and ground truth information for every dataset. In addition, we provide the benchmark tasks and results from these papers or recent competitions. We further discuss gaps and challenges in this domain. We advocate for providing conversion tools to common formats (e.g., COCO format for computer vision tasks) and always providing a set of evaluation metrics, instead of just one, to make results comparable across studies. © 2022, The Author(s).

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Dynamic Feature Queue for Surveillance Face Anti-spoofing via Progressive Training

Dynamic Feature Queue for Surveillance Face Anti-spoofing vi...

引用

2023 IEEE/CVF Conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Wang, Keyao Huang, Mouxiao Zhang, Guosheng Yue, Haixiao Zhang, Gang Qiao, Yu China Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology China University of Chinese Academy of Sciences China

ISBN: (纸本)9798350302493

In recent years, face recognition systems have faced increasingly security threats, making it essential to employ Face Anti-spoofing (FAS) to protect against various types of attacks in traditional scenarios like phone unlocking, face payment and self-service security inspection. However, further exploration is required to fully secure FAS in long-distance settings. In this paper, we propose two contributions to enhance the security of face recognition systems: Dynamic Feature Queue (DFQ) and Progressive Training Strategy (PTS). DFQ converts the conventional binary classification task into a multi-classification task. It treats live samples as a closed set and attack samples as an open set by using a dynamic queue that stores the features of spoofing samples and updates them. On the other hand, PTS targets difficult samples and iteratively adds them in batches for training. The proposed PTS divides the entire training set into blocks, trains only a small portion of the data, and gradually increases the training data with each stage while also incorporating low-scoring positive samples and high-scoring spoof samples from the test set. These two contributions complement each other by enhancing the model's ability to generalize and defend against various types of attacks, making the face recognition system more secure and reliable. Our proposed methods have achieved top performance on ACER metric with 4.73% on the SuHiFiMask dataset [11] and won the first prize in Surveillance Face Anti-spoofing track of the Challenge@CVPR 2023. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Region-based image annotation using asymmetrical support vector machine-based multiple-instance learning

Region-based image annotation using asymmetrical support vec...

引用

2006 IEEE computer Society Conference on computer vision and pattern recognition, CVPR 2006

作者： Yang, Changbo Dong, Ming Hua, Jing Machine Vision and Pattern Recognition Lab. Department of Computer Science Wayne State University Detroit MI 48202 Department of Computer Science Wayne State University Detroit MI 48202

ISBN: (纸本)0769525970

In region-based image annotation, keywords are usually associated with images instead of individual regions in the training data set. This poses a major challenge for any learning strategy. In this paper, we formulate image annotation as a supervised learning problem under Multiple-Instance Learning (MIL) framework. We present a novel Asymmetrical Support Vector Machine-based MIL algorithm (ASVM-MIL), which extends the conventional Support Vector Machine (SVM) to the MIL setting by introducing asymmetrical loss functions for false positives and false negatives. The proposed ASVM-MIL algorithm is evaluated on both image annotation data sets and the benchmark MUSK data sets. © 2006 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Mathematics of Surfaces XIII 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Edwin R. Hancock Ralph R. Martin Malcolm A. Sabin

ISBN: (数字)9783642035968

ISBN: (纸本)9783642035951

This book constitutes the refereed proceedings of the 13th IMA International Conference on the Mathematics of Surfaces held in York, UK in September 2009. The papers in the present volume include seven invited papers, as well as 16 submitted papers. The topics covered include subdivision schemes and their continuity, polar patchworks, compressive algorithms for PDEs, surface invariant functions, swept volume parameterization, Willmore flow, computational conformal geometry, heat kernel embeddings, and self-organizing maps on manifolds, mesh and manifold construction, editing, flattening, morphing and interrogation, dissection of planar shapes, symmetry processing, morphable models, computation of isophotes, point membership classification and vertex blends. Surface types considered encompass polygon meshes as well as parametric and implicit surfaces.

关键词： Discrete Mathematics in computer Science Algorithm Analysis and Problem Complexity computer Graphics Math Applications in computer Science Geometry Computational Science and Engineering

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：