检索结果-内蒙古大学图书馆

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Shiqiang Li Hussain Dawood Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

Dimension reduction methods are often used to analyzing high dimensional data, linear dimension methods are commonly used due to their simple geometric interpretations and for effective computational cost. Dimension reduction plays an important role for feature selection. In this paper, we have given a detailed comparison of state-of-the-art linear dimension reduction methods like principal component analysis (PCA), random projections (RP), and locality preserving projections (LPP). We have determined which dimension reduction method performs better under the FastTag image annotation framework. Experiments are conducted on three standard bench mark image datasets such as CorelSk, IAPRTC-12 and ESP game to compare the efficiency, effectiveness and also memory usage. A detailed comparison among the aforementioned dimension reduction method is given.

关键词： Principal component analysis Benchmark testing Kernel Random access memory Customer relationship management

来源：评论

学校读者我要写书评

暂无评论

Removal of random-valued impulse noise by Khalimsky grid

Removal of random-valued impulse noise by Khalimsky grid

引用

Asia Pacific Conference on Multimedia and Broadcasting (APMediaCast)

作者： Hussain Dawood Hassan Dawood Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

In this paper, based on Khalimsky grid, a new Random-valued Impulse noise identification and removal method is proposed. Khalimsky grid can presents the neighborhood relationship among the pixels in the sliding window, effectively. The local statistics of Khalimsky grid is used to define an adaptive threshold range to identify the central pixel in current sliding window as noisy or noise free in an iterative way. The identified noisy pixel is replaced by local statistics of propose vertical direction based noise removal method. The performance of the propose method is evaluated on different test images and compared with state-of-the-art methods. Experimental results show that the propose method can identify the impulse noise, as well as can preserve the detailed information of an image, efficiently.

关键词： Noise Noise measurement Tin Multimedia communication Filtering algorithms Asia Digital multimedia broadcasting

来源：评论

学校读者我要写书评

暂无评论

Scene understanding based on Multi-Scale Pooling of deep learning features

Scene understanding based on Multi-Scale Pooling of deep lea...

引用

2015 International Conference on Automation,Mechanical Control and Computational Engineering(AMCCE 2015)

作者： DongYang Li Yue Zhou Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University

ISBN: (纸本)9781510803084

Deep convolutional neural networks(CNNs) have recently shown impressive performance as generic representation for recognition. However, the feature extracted from global CNNs lack geometric invariance, which limits their robustness for classification and detection of highly variable *** improve the invariance of the features without degrading their discriminative power and speed up the calculation, we follow the next two method. Firstly, we adopt the scheme called multi-scale orderless pooling(MOP-CNN) which extracts CNNs activation from local patches of the image at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. Second, to speed up the calculation, we adapt the SPP-net as the CNNs architecture. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions(sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. On the challenging SUN397 Scenes classification datasets, our method achieves competitive classification results.

关键词： CNNs MOP-CNN SPP-net Scenes understanding

来源：评论

学校读者我要写书评

暂无评论

A nearest neighbor search method for image matching based on ORB

引用

Journal of Information and Computational Science 2015年第7期12卷 2691-2700页

作者： Zou, Jiancheng Wang, Xiaofei Institute of Image Processing and Pattern Recognition North China University of Technology Beijing China

ORB algorithm is one of the widely used local image feature matching methods. In order to increase the speed of ORB matching, this paper uses a Nearest Neighbor (NN) search method to replace the Hamming distance and proposes a Nearest Neighbor search method for image matching based on ORB. Firstly, the image feature points are detected by FAST and then the corners orientations are determined. Meanwhile, the corresponding binary descriptors with BRIEF are obtained. Finally the feature points can be matched by finding the nearest Euclidean distances. Experimental results show that the new algorithm significantly enhances the matching speed. Copyright © 2015 Binary Information Press.

关键词： image matching

来源：评论

学校读者我要写书评

暂无评论

A Hybrid image Feature Descriptor for Classification

A Hybrid Image Feature Descriptor for Classification

引用

International Conference on Computational Intelligence and Security

作者： Hassan Dawood Hussian Dawood Ping Guo Image Processing and pattern Recognition Laboratory Beijing Normal University Beijing China Department of Computer Engineering University of Engineering and Technology Taxila Pakistan Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

Feature extraction methods have an important role in image classification. In this paper, a hybrid texture feature descriptor is proposed by utilizing the attributes of two complementary features, PRICoLBP and LPQ. PRICoLBP performs well in the case of geometric and photometric variations however it does not properly express the local texture of an image, while LPQ method performs well for the local structure of an image. We propose to use the hybrid scheme by combining the properties of PRICoLBP and LPQ and name it as Pair wise Rotation Invariant Co-occurrence Local Phase Quantization (PRICLPQ). Standard texture and material datasets have been used to verify the robustness of proposed hybrid scheme. The experiments show that the proposed hybrid scheme outperforms the state-of-the-art feature extraction methods like LBP, LPQ, CLBP, LBPV, SIFT, MSLBP, Lazebnik and PRICoLBP in term of accuracy.

关键词： Feature extraction Histograms Robustness Training Quantization (signal) Support vector machines Yttrium

来源：评论

学校读者我要写书评

暂无评论

A comparative study of different feature mapping methods for image annotation

A comparative study of different feature mapping methods for...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Yiren Wang Hassan Dawood Qian Yin Ping Guo the Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China the Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Computer Science Department Beijing Normal University Beijing China

Automatic image annotation and tagging is necessary for indexing and searching of images using querying a text. It is widely used in search engines like Google, Yahoo, Baidu, etc. Fast image Tagging (FastTag) algorithm is proposed to accelerate image annotation process, while keeping the precision of automatic image annotation results. Feature mapping is used to map image features vectors onto higher dimensional feature space. Feature mapping methods plays an important role in automatic image annotation. In this paper, we have compared 6 kernels, among which four kernels are used in homogeneous feature mapping and two kernels are used in discriminative tree based feature mapping, to investigate which feature mapping performs better for automatic image annotation. The performance of these methods has been analyzed by conducting intensive experiments on three different datasets as used by FastTag algorithm in their experiments. We have found that the homogeneous feature mapping with χ 2 kernel is more suitable when used in FastTag algorithm in terms of precision, recall, FI score and N+ measures, and with a relatively acceptable performance.

关键词： Phase change materials Search engines Kernel Indexing Histograms

来源：评论

学校读者我要写书评

暂无评论

NSLIC: SLIC SUPERPIXELS BASED ON NONSTATIONARITY MEASURE

NSLIC: SLIC SUPERPIXELS BASED ON NONSTATIONARITY MEASURE

引用

IEEE International Conference on image processing

作者： Shaoyong Jia Shijie Geng Yun Gu Jie Yang Pengfei Shi Yu Qiao Institue of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

Superpixels become more and more popular as image preprocessing step in computer vision applications. In this paper, we propose an improved simple linear iterative clustering (SLIC) superpixel approach based on nonstationarity measure (NSM), which is called nSLIC. An adjustive distance measure is developed in the five-dimensional [labxy] space. The nSLIC superpixel replaces the predefined fixed value of compactness parameter by the nonstationarity measure map of each image, which exploits the image information and is therefore adaptive to the color feature of the image. It also avoids the difficulty of pre-setting compactness parameter and reduces the parameters needed setting to only one indeed. The nSLIC superpixel improves not only segmentation quality bust also computational efficiency by the way of achieving faster convergence. Experiments done on BSD500 dataset show that nSLIC adheres better to image edges meanwhile producing regular and compact superpixels as much as possible, compared to various popular versions of SLIC.

关键词： Nonstationarity measure NSLIC Superpixel images color feature imagery (Psychotherapy) image information distance measurement compactness computer vision image edge image Self tuning slicking NSM

来源：评论

学校读者我要写书评

暂无评论

RERANKING OF PERSON RE-IDENTIFICATION BY MANIFOLD-BASED APPROACH

RERANKING OF PERSON RE-IDENTIFICATION BY MANIFOLD-BASED APPR...

引用

IEEE International Conference on image processing

作者： Shuai Huang Yun Gu Jie Yang Pengfei Shi Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

Person re-identification (RE-ID) aims at associating the same pedestrian over non-overlapping surveillance scenes. A large number of approaches have emerged in recent years, and they mainly focus on designing middle or high level features to highlight the most discriminative aspects of pedestrians. Due to the nonrigid structure of pedestrians, it is difficult to reidentify pedestrians by low-level features. We investigate the results of conventional person RE-ID approaches, and find that the inadequate utilization of low-level features lead to the poor performance. In this work, we propose a novel framework to utilize the low-level visual features in a more effective way. Given a result obtained from the conventional person RE-ID method, the framework returns a more reasonable result. The framework is extended from the manifold ranking method, and several adjustments are made taking the requirements of person RE-ID into consideration. Our framework is validated through experiments on two person RE-ID datasets (VIPeR and ETHZ), and results from four different conventional approaches show significant improvement.

关键词： Re-identification Manifold Reranking Manifolds Pedestrians LOW LEVEL Persons Frameworks

来源：评论

学校读者我要写书评

暂无评论

UPSAMPLING THE DEPTH MAP WITH ITS OWN PROPERTIES

UPSAMPLING THE DEPTH MAP WITH ITS OWN PROPERTIES

引用

IEEE International Conference on image processing

作者： Wei Liu Penglin Li Jie Yang Pengfei Shi Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

In this paper, we present a novel method to upsample the depth map obtained by the Time-of-Flight (ToF) camera with the guidance of the companion high resolution color image. The problem is modeled with an optimization framework where we use a novel exponential function as the error norm. By using this novel error norm, our model could take the properties of the depth map itself into account. Depth discontinuity cues are obtained not only from the color image but also the depth map itself. To further enhance the performance, we perform a data driven selection of the parameter in the model to better fit the property of the depth map. Experimental results show that our method has excellent performance in smoothing the noise, preserving sharp depth discontinuities and suppressing the texture copy effect.

关键词： Bilateral filter Optimization Depth map upsampling ToF

来源：评论

学校读者我要写书评

暂无评论

CROSS-MODALITY HASHING WITH PARTIAL CORRESPONDENCE

CROSS-MODALITY HASHING WITH PARTIAL CORRESPONDENCE

引用

IEEE International Conference on image processing

作者： Yun Gu Haoyang Xue Jie Yang Pengfei Shi Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

Learning a hashing function for cross-media search is very desirable due to its low storage cost and fast query speed. However, the data crawled from Internet cannot always guarantee good correspondence among different modalities which affects the learning for hashing function. In this paper, we focus on cross-modal hashing with partially corresponded data. The data without full correspondence are made in use to enhance the hashing performance. The experiments on Wiki and NUS-WIDE datasets demonstrates that the proposed method outperforms some state-of-the-art hashing approaches with fewer correspondence information.

关键词： Cross-modality Hashing Partial Correspondence Multimedia Search

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：