检索结果-内蒙古大学图书馆

4th International Conference on Intelligence Science and Big Data Engineering, IScIDE 2013

作者： Zhang, Baochang Liu, Juan Gao, Yongsheng Liu, Jianzhuang Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering BeiHang University Beijing 100191 China School of Engineering Griffith University Australia Shenzhen Key Lab for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9783642420566

This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing;2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design;and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance matrix to simultaneously select appropriate base classifiers with minimized relevance. Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Color constancy and non-uniform illumination: Can existing algorithms work?

Color constancy and non-uniform illumination: Can existing a...

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Michael Bleier Christian Riess Shida Beigpour Eva Eibenberger Elli Angelopoulou Tobias Tröger André Kaup Pattern Recognition Lab University of Erlangen-Nuremberg Germany Computer Vision Center Universidad Autónoma de Barcelona Spain Multimedia Communications and Signal Processing University of Erlangen-Nuremberg Germany

The color and distribution of illuminants can significantly alter the appearance of a scene. The goal of color constancy (CC) is to remove the color bias introduced by the illuminants. Most existing CC algorithms assume a uniformly illuminated scene. However, more often than not, this assumption is an insufficient approximation of real-world illumination conditions (multiple light sources, shadows, interreflections, etc.). Thus, illumination should be locally determined, taking under consideration that multiple illuminants may be present. In this paper we investigate the suitability of adapting 5 state-of-the-art color constancy methods so that they can be used for local illuminant estimation. Given an arbitrary image, we segment it into superpixels of approximately similar color. Each of the methods is applied independently on every superpixel. For improved accuracy, these independent estimates are combined into a single illuminant-color value per superpixel. We evaluated different fusion methodologies. Our experiments indicate that the best performance is obtained by fusion strategies that combine the outputs of the estimators using regression.

关键词： Image color analysis Lighting Databases Light sources Image segmentation Estimation Bayesian methods

来源：评论

学校读者我要写书评

暂无评论

Multiple Transfer Learning and Multi-label Balanced Training Strategies for Facial AU Detection In the Wild

Multiple Transfer Learning and Multi-label Balanced Training...

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Sijie Ji Kai Wang Xiaojiang Peng Jianfei Yang Zhaoyang Zeng Yu Qiao Nanyang Technological University Singapore ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science Sun Yat-Sen University China

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

This paper 1 presents SIAT-NTU solution and results of facial action unit (AU) detection in the EmotiNet Challenge 2020. The task aims to detect 23 AUs from facial images in the wild, and its main difficulties lie in the imbalanced AU distribution and discriminative feature learning. We tackle these difficulties from the following aspects. First, to address the unconstrained heterogeneity of in-the-wild images, we detect and align faces with multi-task convolutional neural networks (MTCNN). Second, by using multiple transfer strategies, we pre-train large CNNs on multiple related datasets, e.g. face recognition datasets and facial expression datasets, and fine-tune them on the EmotiNetdataset. Third, we employ a multi-label balanced sampling strategy and a weighted loss to mitigate the imbalance problem. Last but not the least, to further improve performance, we ensemble multiple models and optimize the thresholds for each AU. Our proposed solution achieves an accuracy of 90.13% and F1 of 44.10% in the final test phase. Our Code is available at: https://***/kaiwang960112/enc2020_au_detection.

关键词： Gold Task analysis Feature extraction Face recognition Training Mathematical model Muscles

来源：评论

学校读者我要写书评

暂无评论

Memory efficient fingerprint verification

Memory efficient fingerprint verification

引用

IEEE International Conference on Image Processing

作者： C. Beleznai H. Ramoser B. Wachmann J. Birchbauer H. Bischof W. Kropatsch Advanced Computer Vision Austrian Research Centre Seibersdorf Vienna Austria Programm-und Systementwicklung Siemens AG Österreich Graz Austria Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria

Fingerprint recognition and verification are often based on local fingerprint features, usually ridge endings or terminations, also called minutiae. By exploiting the structural uniqueness of the image region around a minutia, the fingerprint recognition performance can be significantly enhanced. However, for most fingerprint images the number of minutia image regions (MIRs) becomes dramatically large, which imposes - especially for embedded systems - an enormous memory requirement. Therefore, we are investigating different algorithms for compression of minutia regions. The requirement for these algorithms is to achieve a high compression rate (about 20) with minimum loss in the matching performance of minutia image region matching. We investigate the matching performance for compression algorithms based on the principal component and the wavelet transformation. The matching results are presented in form of normalized ROC curves and interpreted in terms of compression rates and the MIR dimension.

关键词： Fingerprint recognition Image coding computer vision Image recognition Image processing Image matching Embedded system Performance loss Biometrics Character recognition

来源：评论

学校读者我要写书评

暂无评论

Optimal sub-shape models by minimum description length

Optimal sub-shape models by minimum description length

引用

Conference on computer vision and pattern recognition (CVPR)

作者： G. Langs P. Peloschek H. Bischof Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria Department of Clinical Radiology Vienna Medical University Vienna Austria

Active shape models are powerful and widely used tool to interpret complex image data. By building models of shape variation they enable search algorithms to use a priori knowledge in an efficient and gainful way. However, due to the linearity of PCA, non-linearities like rotations or independently moving sub-parts in the data can deteriorate the resulting model considerably. Although non-linear extensions of active shape models have been proposed and application specific solutions have been used, they still need a certain amount of user interaction during model building. In this paper the task of building/choosing optimal models is tackled in a more generic information theoretic fashion. In particular, we propose an algorithm based on the minimum description length principle to find an optimal subdivision of the data into sub-parts, each adequate for linear modeling. This results in an overall more compact model configuration. Which in turn leads to a better model in terms of modes of variations. The proposed method is evaluated on synthetic data, medical images and hand contours.

关键词： Active shape model Biomedical imaging Principal component analysis computer vision Linearity Polynomials pattern recognition computer graphics Radiology Image processing

来源：评论

学校读者我要写书评

暂无评论

Self-supervised multi-view stereo via effective co-segmentation and data-augmentation

arXiv

引用

arXiv 2021年

作者： Xu, Hongbin Zhou, Zhipeng Qiao, Yu Kang, Wenxiong Wu, Qiuxia ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shanghai AI Lab Shanghai China South China University of Technology Guangzhou China

Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multiview stereo (MVS). However, existing methods rely on the assumption that the corresponding points among different views share the same color, which may not always be true in practice. This may lead to unreliable self-supervised signal and harm the final reconstruction performance. To address the issue, we propose a framework integrated with more reliable supervision guided by semantic co-segmentation and data-augmentation. Specially, we excavate mutual semantic from multi-view images to guide the semantic consistency. And we devise effective data-augmentation mechanism which ensures the transformation robustness by treating the prediction of regular samples as pseudo ground truth to regularize the prediction of augmented samples. Experimental results on DTU dataset show that our proposed methods achieve the state-of-the-art performance among unsupervised methods, and even compete on par with supervised methods. Furthermore, extensive experiments on Tanks&Temples dataset demonstrate the effective generalization ability of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Blind path obstacle detector using smartphone camera and line laser emitter

Blind path obstacle detector using smartphone camera and lin...

引用

International Conference on Technology and Innovation in Sports, Health and Wellbeing (TISHW)

作者： Rimon Saffoury Peter Blank Julian Sessner Benjamin H. Groh Christine F. Martindale Eva Dorschky Joerg Franke Bjoern M. Eskofier Digital Sports Group Pattern Recognition Lab Department of Computer Science Institute for Factory Automation and Production Systems Friedrich-Alexander University Erlangen-Numberg (FAU) Erlangen Germany

ISBN: (纸本)9781509057283

Visually impaired people find navigating within unfamiliar environments challenging. Many smart systems have been proposed to help blind people in these difficult, often dangerous, situations. However, some of them are uncomfortable, difficult to obtain or simply too expensive. In this paper, a low-cost wearable system for visually impaired people was implemented which allows them to detect and locate obstacles in their locality. The proposed system consists of two main hardware components, a laser pointer ($12) and an android smart phone, making our system relatively cheap and accessible. The collision avoidance algorithm uses image processing to measure distances to objects in the environment. This is based on laser light triangulation. This obstacle detection is enhanced by edge detection within the captured image. An additional feature of the system is to recognize and warn the user when stairs are present in the camera's field of view. Obstacles are brought to the user's attention using an acoustic signal. Our system was shown to be robust, with only 5 % false alarm rate and a sensitivity of 90 % for 1 cm wide obstacles.

关键词： Measurement by laser beam Laser feedback Cameras Lasers Smart phones Navigation

来源：评论

学校读者我要写书评

暂无评论

Suppressing Uncertainties for Large-Scale Facial Expression recognition

Suppressing Uncertainties for Large-Scale Facial Expression ...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Kai Wang Xiaojiang Peng Jianfei Yang Shijian Lu Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Nanyang Technological University Singapore

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. These uncertainties suspend the progress of large-scale Facial Expression recognition (FER) in data-driven deep learning era. To address this problelm, this paper proposes to suppress the uncertainties by a simple yet efficient Self-Cure Network (SCN). Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over FER dataset to weight each sample in training with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group. Experiments on synthetic FER datasets and our collected WebEmotion dataset validate the effectiveness of our method. Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with \textbf{88.14}\% on RAF-DB, \textbf{60.23}\% on AffectNet, and \textbf{89.35}\% on FERPlus.

关键词： Uncertainty Face recognition Feature extraction Noise measurement Training Face computer vision

来源：评论

学校读者我要写书评

暂无评论

Suppressing uncertainties for large-scale facial expression recognition

arXiv

引用

arXiv 2020年

作者： Wang, Kai Peng, Xiaojiang Yang, Jianfei Lu, Shijian Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Nanyang Technological University Singapore

Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. These uncertainties lead to a key challenge of large-scale Facial Expression recognition (FER) in deep learning era. To address this problem, this paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial images. Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over mini-batch to weight each training sample with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group. Experiments on synthetic FER datasets and our collected WebEmotion dataset validate the effectiveness of our method. Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with 88.14% on RAF-DB, 60.23% on AffectNet, and 89.35% on FERPlus. The code will be available at https://***/kaiwang960112/Self-Cure-Network. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Signature segmentation and recognition from scanned documents

Signature segmentation and recognition from scanned document...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Ranju Mandal Partha Pratim Roy Umapada Pal Michael Blumenstein School of Information and Communication Technology Griffith University Queensland Australia Automation Engineering Department Synchromedia Lab Montreal Canada Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Signature as a query is important for content-based document image retrieval from a scanned document repository. This paper presents a two-stage approach towards automatic signature segmentation and recognition from scanned document images. In the first stage, signature blocks are segmented from the document using word-wise component extraction and classification. Gradient based features are extracted from each component at the word level to perform the classification task. In the 2nd stage, SIFT (Scale-Invariant Feature Transform) descriptors and Spatial Pyramid Matching (SPM)-based approaches are used for signature recognition. Support Vector Machines (SVMs) are employed as the classifier for both levels in this experiment. The experiments are performed on the publicly available “Tobacco-800” and GPDS [1] datasets and the results obtained from the experiments are promising.

关键词： Image segmentation Industries Vector quantization Hidden Markov models

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：