检索结果-内蒙古大学图书馆

International Conference on computer vision (ICCV)

作者： J.-K. Kamarainen M. Hamouz J. Kittler P. Paalanen J. Ilonen A. Drobchenko Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey UK Machine Vision and Pattern Recognition Research Group Lappeenranta University of Technology Finland

In this paper we apply state-of-the-art approach to object detection and localisation by incorporating local descriptors and their spatial configuration into a generative probability model. In contrast to the recent semi- supervised methods we do not utilise interest point detectors, but apply a supervised approach where local image features (landmarks) are annotated in a training set and therefore their appearance and spatial variation can be learnt. Our method enables working in purely probabilistic search spaces providing a MAP estimate of object location, and in contrast to the recent methods, no background class needs to be formed. Using the training set we can estimate pdfs for both spatial constellation and local feature appearance. By applying an inference bias that the largest pdf mode has probability one, we are able to combine prior information (spatial configuration of the features) and observations (image feature appearance) into posterior distribution which can be generatively sampled, e.g. using MCMC techniques. The MCMC methods are sensitive to initialisation, but as a solution, we also propose a very efficient and accurate RANSAC-based method for finding good initial hypotheses of object poses. The complete method can robustly and accurately detect and localise objects under any homography.

关键词： Object detection Robustness Solid modeling Speech processing Signal processing Machine vision pattern recognition Signal generators Detectors Phase detection

来源：评论

学校读者我要写书评

暂无评论

A Discriminative Framework for Object recognition

A Discriminative Framework for Object Recognition

引用

International Conference on Mechatronics (ICM)

作者： Hongwei Li Jian Cheng Hanqing Lu National Laboratory Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China

In this paper, we present a discriminative approach to learn and recognize the object classes from unsegmented cluttered scenes in a scale invariant manner. A multiscale algorithm for the selection of salient regions of an image is used to select keypoints and their scale in the image. The PCA-SIFT method is used to describe these keypoints in a compact form. For each object class the probability of local features is modeled by a conditional random fields (CRF). In the learning stage, the parameters of CRF are estimated from feature vectors given the labels in a maximum likelihood framework. In the recognition stage, we take the label for the image to the most likely class under the CRF models. This method achieves good classification results on motorbikes and airplanes database.

关键词： Object recognition Detectors Entropy computer vision pattern recognition Layout Maximum likelihood estimation Mechatronics Automation Image recognition

来源：评论

学校读者我要写书评

暂无评论

ROI progressive image transmission based on wavelet transform and human visual specialties

ROI progressive image transmission based on wavelet transfor...

引用

International Conference on Wavelet Analysis and pattern recognition (ICWAPR)

作者： Ji-Ming Zheng Da-Wei Zhou Jin-Ling Geng College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

Based on the properties of integer wavelet transform and multiresolution analysis and combined with human visual specialties, an improved region of interest (ROI) progressive image transmission algorithm is proposed. With no impact on the subjective quality of ROI image, in the first instance, the coefficients in the ROI and the important wavelet coefficients for human vision are transmitted. Moreover, to indicate the relative importance of the BG with respect to the ROI, an expansion factor S for background (BG) image transmission and its formula is presented. Depending on the factor, the transmission of BG image can be controlled at different bit rates, so that the users can achieve the image with better subjective quality. Meanwhile, the algorithm could improve the visual quality of image and enhance the efficiency of the image transmission. The experimental results prove that the proposed algorithm is effective and the expansion factor could control the image transmission.

关键词： Image communication Wavelet transforms Humans Wavelet analysis Multiresolution analysis Image coding Image analysis pattern analysis pattern recognition Internet

来源：评论

学校读者我要写书评

暂无评论

基于显微图像模式识别的粉丝品质检测研究

引用

大连理工大学学报 2007年第3期47卷 378-382页

作者：郭明恩欧宗瑛孙祖莉王洪来大连理工大学机械工程学院CAD&CG研究所辽宁大连116024 烟台大学山东烟台264005 烟台出入境检验检疫局山东烟台264001

粉丝由植物淀粉加工而成.鉴别粉丝中淀粉的种类及成分比例对食品的营养与安全具有重要而现实的意义.目前商检中主要依靠感官评价,可靠性差.为此提出以图像处理、模式识别、人工神经网络为基础的粉丝计算机自动分类和检测新方法.以粉丝... 详细信息

粉丝由植物淀粉加工而成.鉴别粉丝中淀粉的种类及成分比例对食品的营养与安全具有重要而现实的意义.目前商检中主要依靠感官评价,可靠性差.为此提出以图像处理、模式识别、人工神经网络为基础的粉丝计算机自动分类和检测新方法.以粉丝组织的显微图像为基础,运用灰度共生矩阵和分形理论提取显微图像的特征,并将提取出来的特征用做神经网络淀粉品质分类的输入,建立了粉丝中淀粉品质的自动检测系统.实验结果表明,该方法可行,结果较好.

关键词：粉丝图像处理特征提取模式识别

来源：评论

学校读者我要写书评

暂无评论

2DCCA: A Novel Method for Small Sample Size Face recognition

2DCCA: A Novel Method for Small Sample Size Face Recognition

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Cai-rong Zou Ning Sun Zhen-hai Ji Li Zhao Foshan University Foshan China Department of Radio Engineering South-East University Nanjing China

In the traditional canonical correlation analysis (CCA) based face recognition methods, the size of sample is always smaller than the dimension of sample. This problem is so called the small sample size (SSS) problem. In order to solve this problem, a new supervised learning method called two-dimensional CCA (2DCCA) is developed in this paper. Different from traditional CCA method, 2DCCA directly extracts the features from image matrix rather than matrix-to-vector transformation. In practice, the covariance matrix extracted by 2DCCA is always full rank. Hence the small sample size (SSS) problem can be effectively dealt with by this new developed method. The theory foundation of 2DCCA method is firstly developed, and the construction method for the class-membership matrix Y which is used to precisely represent the relationship between samples and classes in the 2DCCA framework is then clarified. Simultaneously, the analytic form of the generalized inverse of such class-membership matrix is derived. From our experiment results on face recognition, we clearly find that not only the SSS problem can be effectively solved, but also better recognition performance than several other CCA based methods has been achieved

关键词： Face recognition Covariance matrix Feature extraction Multidimensional systems Principal component analysis Sun Supervised learning Multidimensional signal processing Biomedical imaging pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A System for Off-Line Oriya Handwritten Character recognition Using Curvature Feature

A System for Off-Line Oriya Handwritten Character Recognitio...

引用

International Conference on Information Technology (ICIT)

作者： U. Pal T. Wakabayashi F. Kimura Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Graduate School of Engineering Mie University Tsu Mie Japan

In this paper we present a system towards the recognition of off-line Oriya handwritten characters. Since most of the Oriya characters have curve-like stroke, we use curvature feature for the recognition purpose. To get the feature, at first, the input image is size normalized and segmented into 49times49 blocks. Curvature is then computed using bi-quadratic interpolation method and quantized into 3 levels according to concave, linear and convex regions. Next direction of gradient is quantized into 32 levels with pi/16 intervals, and strength of the gradient is accumulated in each of the 32 directions and in each of the 3 curvature levels of every block. A spatial resolution is made to get 7times7 blocks from 49times49 blocks and a directional resolution is made to get 8 directions from 32 directions. Using curvature features for 3 levels we get 1176 (7times7 blocks times 8 directions times 3 levels) dimensional features. Finally using principal component analysis we reduce the dimension 1176 to 392 and this 392 dimensional feature vector is fed to a quadratic classifier for recognition. We tested 18190 samples of Oriya handwritten samples and obtained 94.60% accuracy from our proposed system.

关键词： Character recognition Shape Handwriting recognition computer vision Spatial resolution Speech recognition Information technology pattern recognition Image segmentation Interpolation

来源：评论

学校读者我要写书评

暂无评论

Object Extraction by Spatio-Temporal Assembling

Object Extraction by Spatio-Temporal Assembling

引用

IEEE International Conference on Image Processing

作者： Xiaoke Qin Liang Tang Jie Zhou China Hewlett Packard Laboratories China

Among various algorithms for vision-based traffic monitoring, spatio-temporal (ST) slice analysis is attractive by computing over a larger temporal scale. However, it is unsuitable for further pattern recognition, since the conventional ST slice cannot preserve the spatial relationship of the original object image. In this paper, we propose a novel algorithm for accurate traffic object extraction. Compared with previous ST algorithms depending on one line per frame, we assemble the object based on foreground strips obtained from each frame and carefully designed motion estimation. Thus, both the spatial and temporal information is used more effectively. Applications in real canal traffic scenes show the advantages of our algorithm.

关键词： Assembly Algorithm design and analysis Monitoring computer vision pattern recognition Data mining Strips Motion estimation Irrigation Layout

来源：评论

学校读者我要写书评

暂无评论

Rotation Invariant Shape Contexts based on Feature-space Fourier Transformation

Rotation Invariant Shape Contexts based on Feature-space Fou...

引用

International Conference on Image and Graphics (ICIG)

作者： Su Yang Yuanyuan Wang Department of Computer Science and Engineering Fudan University Shanghai China Department of Electronic Engineering Fudan University Shanghai China

We propose a new pixel-level shape descriptor. First, shape contexts are computed. Then, 2D FFT is performed on each 2D histogram from shape contexts. Such a scheme solves the rotation-invariance problem of shape contexts based on the shift theorem of Fourier transformation while does not increase the computational complexity. Theoretical proof and experimental validation are provided.

关键词： Shape Computational complexity Robustness Histograms pattern matching computer vision pattern recognition computer graphics computer science Pixel

来源：评论

学校读者我要写书评

暂无评论

Motion Analysis of Endovascular Stent-Grafts by MDL Based Registration

Motion Analysis of Endovascular Stent-Grafts by MDL Based Re...

引用

International Conference on computer vision (ICCV)

作者： Georg Langs Nikos Paragios Rene Donner Pascal Desgranges Alain Rahmouni Hicham Kobeiter GALEN Group Laboratoire de Mathématiques Appliquées aux Systàmes Ecole Centrale de Paris France Institute for Computer Graphics and Vision Graz University of Technology Austria Pattern Recognition and Image Processing Group University of Technology Vienna Austria University of Paris XII Paris France

The endovascular repair of a traumatic rupture of the thoracic aorta - that would otherwise lead to the death of the patient - is performed by delivering a stent-graft into the vessel at the rupture location. The age range of the affected patients is large and the stent-graft will stay in the body for the remaining life. The technique is relatively new, and no experience with regard to long-term effects, and durability exists. To predict long-term complications, such as ruptures or destructive interactions with surrounding tissue during the life of the patient, it is important to understand the - rather intense and constant - movement of the stent- graft during the cardiac cycle. A computed tomography with heart gating (gated CT) acquires sequences that show the region of the stent-graft at different time points. We analyze the motion of stent-grafts with a model based approach. Stent-grafts are represented as sparse sets of axis points extracted from the gated CT, and motion patterns are captured by a minimum description length based group-wise registration of the stent-graft at different time points. No parameterization or a priori definition of the topology is necessary, and highly variable elasticity properties in the data volume can by accounted for by the sparse statistical model, that captures correlations and motion components of the stent-graft. We report results for deformation models and registration accuracy for 5 patients.

关键词： Motion analysis Computed tomography Biomedical imaging Heart Buildings computer graphics pattern recognition Image processing Hospitals Data mining

来源：评论

学校读者我要写书评

暂无评论

We don't need no bounding-boxes: Training object class detectors using only human verification

We don't need no bounding-boxes: Training object class detec...

引用

IEEE Conference on computer vision and pattern recognition

作者： Dim P. Papadopoulos Jasper R. R. Uijlings Frank Keller Vittorio Ferrari Univ. of Edinburgh Edinburgh UK

ISBN: (纸本)9781467388528

Training object class detectors typically requires a large set of images in which objects are annotated by bounding-boxes. However, manually drawing bounding-boxes is very time consuming. We propose a new scheme for training object detectors which only requires annotators to verify bounding-boxes produced automatically by the learning algorithm. Our scheme iterates between re-training the detector, re-localizing objects in the training images, and human verification. We use the verification signal both to improve re-training and to reduce the search space for re-localisation, which makes these steps different to what is normally done in a weakly supervised setting. Extensive experiments on PASCAL VOC 2007 show that (1) using human verification to update detectors and reduce the search space leads to the rapid production of high-quality bounding-box annotations;(2) our scheme delivers detectors performing almost as good as those trained in a fully supervised setting, without ever drawing any bounding-box;(3) as the verification task is very quick, our scheme substantially reduces total annotation time by a factor 6×-9×.

关键词： Detectors Training Proposals Search problems computer vision Visualization Containers tabu search images detector Training Functional training computer vision CONTAINERS Visualization object class Verification bounding boxes

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：