检索结果-内蒙古大学图书馆

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Saibabu Arigela K. Vijayan Asari Computational Intelligence and Machine Vision Laboratory Department of Electrical and Computer Engineering Old Dominion University Norfolk VA USA

In night time surveillance, there is a possibility of having extremely bright and dark regions in some image frames of a video sequence. A novel non linear image enhancement algorithm for digital images captured under such extremely non-uniform lighting conditions is proposed in this paper. The new technique constitutes three processes viz. adaptive intensity enhancement, contrast enhancement and color restoration. Adaptive intensity enhancement uses a specifically designed nonlinear transfer function which is capable of reducing the intensity of bright regions and at the same time enhancing the intensity of dark regions. Contrast enhancement tunes the intensity of each pixels magnitude based on its surrounding pixels. Finally, a linear color restoration process based on the chromatic information of the input image frame is applied to convert the enhanced intensity image back to a color image.

关键词： Layout Dynamic range Image coding Color Image restoration Image enhancement Displays Histograms Computational intelligence machine vision

来源：评论

学校读者我要写书评

暂无评论

Autonomous Learning of Object Appearances using Colour Contour Frames

Autonomous Learning of Object Appearances using Colour Conto...

引用

Canadian Conference on computer and Robot vision, CRV

作者： P. Forssen A. Moe Department of Computer Science Laboratory for Computational Intelligence BC Canada Computer Vision Laboratory Department of Electrical Engineering Linköping University Linkoping Sweden

In this paper we make use of the idea that a robot can autonomously discover objects and learn their appearances by poking and prodding at interesting parts of a scene. In order to make the resultant object recognition ability more robust, and discriminative, we replace earlier used colour histogram features with an invariant texture-patch method. The texture patches are extracted in a similarity invariant frame which is constructed from short colour contour segments. We demonstrate the robustness of our invariant frames with a repeatability test under general homography transformations of a planar scene. Through the repeatability test, we find that defining the frame using using ellipse segments instead of lines where this is appropriate improves repeatability. We also apply the developed features to autonomous learning of object appearances, and show how the learned objects can be recognised under out-of-plane rotation and scale changes.

关键词： Image segmentation computer vision Layout Testing Solid modeling Laboratories Robot vision systems Object recognition Robustness Histograms

来源：评论

学校读者我要写书评

暂无评论

A hardware-efficient high performance digital architecture for run-time computation of normalized cross correlation

引用

WSEAS Transactions on Circuits and Systems 2006年第9期5卷 1416-1423页

作者： Zhang, Ming Z. Asari, Vijayan K. Computational Intelligence and Machine Vision Laboratory Department of Electrical and Computer Engineering Old Dominion University 231 Kaufman Hall Norfolk VA 23529 United States

A novel architecture for performing high speed computation of normalized cross correlation (NCC) is proposed in this paper. The approach promotes the concept of digital filter design to simplify window related operations and log-domain computations to eliminate all multiplications, divisions, squares, and square-roots utilizing the approximation techniques for efficient estimation of log2 and inverse-log2. The new design is capable of performing run-time calculation of NCC and the energy normalization on the fly, eliminating the frame buffering and frame sized integral tables. A new concept of uniform filter design is also presented to reduce the number of processing element arrays (PEAs) from V PEAs to 2 PEAs for a U × V window. This concept is applied to simplify the calculation of average value and energy in NCC equation. It is observed that the performance of the system with parallel pipelined architecture is able to achieve 178.5 million outputs per second (MOPS), or equivalently 142.8 billion multiplications per second, on Xilinx's Virtex II XC2V6000-4ff1152 FPGA with maximum clock frequency of 178.5MHz with 20 × 20 feature template of 8-bit resolution. Given a 1024 × 1024 data frame, the system can process over 170 frames per second (fps). Similarly, the improved full precision logarithmic module is able to sustain 212.2 MOPS at 212.2MHz maximum clock frequency with 32-bit resolution.

关键词： Digital filters

来源：评论

学校读者我要写书评

暂无评论

Localized Support Vector machines for Classification

Localized Support Vector Machines for Classification

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ming Dong Jing Wu Machine Vision and Pattern Recognition Laboratory Department of Computer Science Wayne State University Detroit MI USA

Support vector machines (SVMs) have been promising methods in pattern recognition because of their solid mathematical foundation. In this paper, we propose a localized SVM classification scheme (LSVM). In which we first cluster the training data in each category, and then train a set of SVMs based on these dusters. The SVMs trained from the clusters in each category that are nearest to the given input pattern are then selected for the final classification. Our experiments on six UCI datasets show that LSVM outperforms the traditional SVM.

关键词： Support vector machines Support vector machine classification Kernel USA Councils Solids machine learning Training data Nails Neural networks Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

O2-03-08

引用

Alzheimer's & Dementia 2007年第3期3卷 S191-S192页

作者： Giovanni B. Frisoni Anna Caroli Cristina Testa Cristina Geroldi Flavio Nobili Ugo P. Guerra Matteo Bonetti Laboratory of Epidemiology Neuroimaging & Telemedicine - IRCCS S.Giovanni di Dio - Fatebenefratelli Brescia Italy AFaR Associazione Fatebenefratelli per la Ricerca Rome Italy Machine Vision Laboratory Department of Mathematics and Computer Science University of Udine Udine Italy Psychogeriatrics Unit - IRCCS S. Giovanni di Dio - FBF Brescia Italy Division of Clinical Neurophysiology Department of Endocrinological and Metabolic Sciences University of Genoa Genoa Italy Department of Nuclear Medicine Ospedali riuniti Bergamo Italy Neuroradiology Service Clinical Institute Città di Brescia Brescia Italy.

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

Conference on computer vision and Pattern Recognition (CVPR)

作者： Changbo Yang Ming Dong Jing Hua Machine Vision and Pattern Recognition Laboratory Department of Computer Science Wayne State University Detroit MI USA Department of Computer Science Wayne State University Detroit MI USA

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.

关键词： machine learning Support vector machines Image retrieval Pattern recognition computer science Training data Supervised learning computer vision Feature extraction Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Finding a Semantic Structure Interactively in Image Databases

Finding a Semantic Structure Interactively in Image Database...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Manjeet Rege Ming Dong Farshad Fotouhi Machine Vision & Pattern Recognition Laboratory Department of Computer Science Wayne State University Detroit MI USA Database & Multimedia Systems Group Department of Computer Science Wayne State University Detroit MI USA

We present a new approach to organize an image database by finding a semantic structure interactively based on multi-user relevance feedback. By treating user relevance feedbacks as weak classifiers and combining them together, we are able to capture the categories in the users' mind and build a semantic structure in the image database. Experiments performed on an image database consisting of general purpose images demonstrate that our system outperforms some of the other conventional methods

关键词： Image databases Feedback Image retrieval machine learning algorithms Support vector machines Support vector machine classification Information retrieval machine vision Pattern recognition Multimedia databases

来源：评论

学校读者我要写书评

暂无评论

Co-clustering Documents and Words Using Bipartite Isoperimetric Graph Partitioning

Co-clustering Documents and Words Using Bipartite Isoperimet...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Manjeet Rege Ming Dong Farshad Fotouhi Machine Vision and Pattern Recognition Laboratory Database and Multimedia Systems GroupDepartment of Computer Science Wayne State University Detroit MI USA Database and Multimedia Systems Group Database and Multimedia Systems GroupDepartment of Computer Science Wayne State University Detroit MI USA

In this paper, we present a novel graph theoretic approach to the problem of document-word co-clustering. In our approach, documents and words are modeled as the two vertices of a bipartite graph. We then propose isoperimetric co-clustering algorithm (ICA) - a new method for partitioning the document-word bipartite graph. ICA requires a simple solution to a sparse system of linear equations instead of the eigenvalue or SVD problem in the popular spectral co-clustering approach. Our extensive experiments performed on publicly available datasets demonstrate the advantages of ICA over spectral approach in terms of the quality, efficiency and stability in partitioning the document-word bipartite graph.

关键词： Bipartite graph Partitioning algorithms Independent component analysis Equations Eigenvalues and eigenfunctions Stability Data mining Random variables Mutual information machine vision

来源：评论

学校读者我要写书评

暂无评论

On the uncertainty inequality as applied to discrete signals

引用

International Journal of Mathematics and Mathematical sciences 2006年第1期2006卷

作者： Venkatesh, Y.V. Raja, S. Kumar Vidyasagar, G. Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore 560012 India Department of Electrical and Computer Engineering Faculty of Engineering National University of Singapore Singapore 117576 Singapore

Given a continuous-time bandlimited signal, the Shannon sampling theorem provides an interpolation scheme for exactly reconstructing it from its discrete samples. We analyze the relationship between concentration (or compactness) in the temporal/spectral domains of the (i) continuous-time and (ii) discrete-time signals. The former is governed by the Heisenberg uncertainty inequality which prescribes a lower bound on the product of effective temporal and spectral spreads of the signal. On the other hand, the discrete-time counterpart seems to exhibit some strange properties, and this provides motivation for the present paper. We consider the following problem: for a bandlimited signal, can the uncertainty inequality be expressed in terms of the samples, using the standard definitions of the temporal and spectral spreads of the signal? In contrast with the results of the literature, we present a new approach to solve this problem. We also present a comparison of the results obtained using the proposed definitions with those available in the literature. Copyright © 2006 Hindawi Publishing Corporation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Co-Clustering Image Features and Semantic Concepts

Co-Clustering Image Features and Semantic Concepts

引用

IEEE International Conference on Image Processing

作者： Manjeet Rege Ming Dong Farshad Fotouhi Department of Computer Science Machine Vision & Pattern Recognition Laboratory Wayne State University Detroit MI USA Database & Multimedia Systems Group Wayne State University Detroit MI USA

In this paper, we present a novel idea of co-clustering image features and semantic concepts. We accomplish this by modelling user feedback logs and low-level features using a bipartite graph. Our experiments demonstrate that (1) incorporating semantic information achieves better image clustering and (2) feature selection in co-clustering narrows the semantic gap, thus enabling efficient image retrieval.

关键词： Feedback Image retrieval Bipartite graph Image databases Clustering algorithms machine vision Pattern recognition Multimedia databases Spatial databases Multimedia systems

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：