检索结果-内蒙古大学图书馆

IEEE Conference on computer vision and pattern recognition

作者： Zhu, Zhenfeng Zhao, Yao Lu, Hanqing Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China Peking Univ Natl Key Lab Machine Percept Beijing Peoples R China Chinese Acad Sci Recongit Inst Automat Natl Lab Pattern Beijing Peoples R China

ISBN: (纸本)9781424411795

Based on multi-cue integration and hierarchical SVM, we present a sequential architecture for efficient car detection under complex outdoor scene in this paper. On the low level, two novel area templates based on edge and interest-point cues respectively are first constructed, which can be applied to forming the identities of visual perception to some extent and thus utilized to reject rapidly most of the negative non-car objects at the cost of missing few of the true ones. Moreover on the high level, both global structure and local texture cues are exploited to characterize the car objects precisely. To improve the computational efficiency of general SVM, a solution approximating based two-level hierarchical SVM is proposed. The experimental results show that the integration of global structure and local texture properties provides more power powerful ability in discrimination of car objects from non-car ones. The final high detection performance also contributes to the utilizing of two novel low level visual cues and the hierarchical SVM.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Synthesising surface matching algorithms using the correspondence framework

引用

pattern recognition and Image Analysis 2007年第2期17卷 199-203页

作者： Planitz, B.M. Maeder, A.J. Williams, J.A. E-Health Research Centre CSIRO ICT Centre Level 20 300 Adelaide Street Brisbane QLD 4001 Australia School of Information Technology and Electrical Engineering University of Queensland St. Lucia QLD 4072 Australia

computer vision tasks such as registration, modeling and object recognition, are becoming increasingly useful in industry. Each of these applications employs correspondence algorithms to compute accurate mappings between partially overlapping surfaces. In industry, it is essential to select an appropriate correspondence algorithm for a given surface matching task. A correspondence framework has recently been proposed to assist in the selection and creation of correspondence algorithms for these tasks. This paper demonstrates how to use the correspondence framework to create a new surface matching algorithm, which uses stages of an existing model matching algorithm. The efficiency with which the new algorithm is created using the correspondence frame work is emphasized. In addition, results show that the new algorithm is both robust and efficient. © Nauka/Interperiodica 2007.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Salvage of Supervision in Weakly Supervised Object Detection

Salvage of Supervision in Weakly Supervised Object Detection

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Sui, Lin Zhang, Chen-Lin Wu, Jianxin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China 4Paradigm Inc Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Weakly supervised object detection (WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper proposes new approaches to utilize these weak and noisy signals effectively, and shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also has the ability to freely use modern FSOD techniques. SoSWSOD achieves 64.4 mAP(50) on VOC2007, 61.9 mAP(50) on VOC2012 and 16.6 mAP(50:95) on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.

关键词： Bridges Visualization computer vision Machine vision Object detection pattern recognition Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Real-time object classification in video surveillance based on appearance learning

Real-time object classification in video surveillance based ...

引用

IEEE Conference on computer vision and pattern recognition

作者： Zhang, Lun Li, Stan Z. Yuan, Xiaotong Xiang, Shiming Chinese Acad Sci Ctr Biomet & Secur Res Inst Automat Natl Lab Pattern Recognit Beijing 100080 Peoples R China

ISBN: (纸本)9781424411795

Classifying moving objects to semantically meaningful categories is important for automatic visual surveillance. However, this is a challenging problem due to the factors related to the limited object size, large intra-class variations of objects in a same class owing to different viewing angles and lighting, and real-time performance requirement in real-world applications. This paper describes an appearance-based method to achieve real-time and robust objects classification in diverse camera viewing angles. A new descriptor, i.e., the Multi-block Local Binary pattern (MB-LBP), is proposed to capture the large-scale structures in object appearances. Based on MB-LBP features, an adaBoost algorithm is introduced to select a subset of discriminative features as well as construct the strong two-class classifier To deal with the non-metric feature value of MB-LBP features, a multi-branch regression tree is developed as the weak classifiers of the boosting. Finally, the Error Correcting Output Code (ECOC) is introduced to achieve robust multi-class classification performance. Experimental results show that our approach can achieve real-time and robust object classification in diverse scenes.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

An investigation of the modified direction feature for cursive character recognition

引用

pattern recognition 2007年第2期40卷 376-388页

作者： Blumenstein, Michael Liu, Xin Yu Verma, Brijesh Griffith Univ Sch Informat & Commun Technol Gold Coast Mail Centre Qld 9726 Australia Univ Cent Queensland Sch Informat Technol Rockhampton Qld 4702 Australia

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset. (c) 2006 pattern recognition Society. Published by Elsevier Ltd. All rights reserved.

关键词： handwritten character recognition pattern recognition image processing and computer vision neural networks

来源：评论

学校读者我要写书评

暂无评论

Equivalence of some common linear feature extraction techniques for appearance-based object recognition tasks

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2007年第5期29卷 896-900页

作者： Asuncion Vicente, M. Hoyer, Patrik O. Hyvarinen, Aapo Miguel Hernandez Univ Dept Ind Syst Engn Elche 03202 Alicante Spain Univ Helsinki Helsinki Inst Informat Technol Basic Res Unit FIN-00014 Helsinki Finland

Recently, a number of empirical studies have compared the performance of PCA and ICA as feature extraction methods in appearance-based object recognition systems, with mixed and seemingly contradictory results. In this paper, we briefly describe the connection between the two methods and argue that whitened PCA may yield identical results to ICA in some cases. Furthermore, we describe the specific situations in which ICA might significantly improve on PCA.

关键词： computer vision object recognition principal component analysis independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Feature Selective Networks for Object Detection 31

Feature Selective Networks for Object Detection

引用

31st IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Zhai, Yao Fu, Jingjing Lu, Yan Li, Houqiang Univ Sci & Technol China Hefei Anhui Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9781538664209

Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted by RoI pooling with little emphasis on these translation-variant feature components. We present feature selective networks to reform the feature representations of Rols by exploiting their disparities among sub-regions and aspect ratios. Our network produces the sub-region attention bank and aspect ratio attention bank for the whole image. The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification. Equipped with a lightweight detection subnetwork, our network gets a consistent boost in detection performance based on general ConvNet backbones (ResNet-101, GoogLeNet and VGG-16). Without bells and whistles, our detectors equipped with ResNet-101 achieve more than 3% mAP improvement compared to counterparts on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets.

关键词： Feature extraction Proposals Object detection Detectors Dimensionality reduction Visualization pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Maximum Entropy Feature Descriptor for Age Invariant Face recognition

A Maximum Entropy Feature Descriptor for Age Invariant Face ...

引用

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Gong, Dihong Li, Zhifeng Tao, Dacheng Liu, Jianzhuang Li, Xuelong Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Comp Vis & Pattern Recognit Beijing 100864 Peoples R China Univ Technol Sydney Fac Engn & IT Ctr Quantum Computat & Intelligent Syst Sydney NSW 2007 Australia Chinese Univ Hong Kong Dept Informat Engn Hong Kong Hong Kong Peoples R China Huawei Technol Co Ltd Media Lab Shenzhen Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Beijing 100864 Peoples R China

ISBN: (纸本)9781467369640

In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition. First, a new maximum entropy feature descriptor (MEFD) is developed that encodes the microstructure of facial images into a set of discrete codes in terms of maximum entropy. By densely sampling the encoded face image, sufficient discriminatory and expressive information can be extracted for further analysis. A new matching method is also developed, called identity factor analysis (IFA), to estimate the probability that two faces have the same underlying identity. The effectiveness of the framework is confirmed by extensive experimentation on two face aging datasets, MORPH (the largest public-domain face aging dataset) and FGNET. We also conduct experiments on the famous LFW dataset to demonstrate the excellent generalizability of our new approach.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Diversity-Enhanced Condensation Algorithm and Its Application for Robust and Accurate Endoscope Three-Dimensional Motion Tracking 27

Diversity-Enhanced Condensation Algorithm and Its Applicatio...

引用

27th IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Luo, Xiongbiao Wan, Ying He, Xiangjian Yang, Jie Mori, Kensaku Nagoya Univ Nagoya Aichi 4648601 Japan Univ Technol Sydney Sydney NSW 2007 Australia Shanghai Jiao Tong Univ Shanghai 200030 Peoples R China

ISBN: (纸本)9781479951178

The paper proposes a diversity-enhanced condensation algorithm to address the particle impoverishment problem which stochastic filtering usually suffers from. The particle diversity plays an important role as it affects the performance of filtering. Although the condensation algorithm is widely used in computer vision, it easily gets trapped in local minima due to the particle degeneracy. We introduce a modified evolutionary computing method, adaptive differential evolution, to resolve the particle impoverishment under a proper size of particle population. We apply our proposed method to endoscope tracking for estimating three-dimensional motion of the endoscopic camera. The experimental results demonstrate that our proposed method offers more robust and accurate tracking than previous methods. The current tracking smoothness and error were significantly reduced from ( 3.7, 4.8) to ( 2.3 mm, 3.2 mm), which approximates the clinical requirement of 3.0 mm.

关键词： Diversity-Enhanced Condensation Algorithm Endoscope 3D Motion Tracking Endoscopic Navigation

来源：评论

学校读者我要写书评

暂无评论

Automatic age estimation based on facial aging patterns

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2007年第12期29卷 2234-2240页

作者： Geng, Xin Zhou, Zhi-Hua Smith-Miles, Kate Deakin Univ Sch Informat Technol & Engn Melbourne Vic 3125 Australia Nanjing Univ Natl Key Lab Novel Software Technol Nanjing 210093 Peoples R China

While recognition of most facial variations, such as identity, expression, and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial variations, aging variation presents several unique characteristics which make age estimation a challenging task. This paper proposes an automatic age estimation method named AGES ( AGing pattern Subspace). The basic idea is to model the aging pattern, which is defined as the sequence of a particular individual's face images sorted in time order, by constructing a representative subspace. The proper aging pattern for a previously unseen face image is determined by the projection in the subspace that can reconstruct the face image with minimum reconstruction error, while the position of the face image in that aging pattern will then indicate its age. In the experiments, AGES and its variants are compared with the limited existing age estimation methods ( WAS and AAS) and some well- established classification methods (kNN, BP, C4.5, and SVM). Moreover, a comparison with human perception ability on age is conducted. It is interesting to note that the performance of AGES is not only significantly better than that of all the other algorithms, but also comparable to that of the human observers.

关键词： computer vision pattern recognition machine learning face and gesture recognition age estimation

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：