检索结果-内蒙古大学图书馆

2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference(ITAIC 2011)

作者： Wu Jiang School of Science Beijing Forestry University Beijing,China Huang Rule Information Centre Beijing Forestry University Beijing,China Xu Ziyue School of Technology Beijing Forestry University Beijing,China Han Ning School of Technology Beijing Forestry University Beijing,China

A novel algorithm for image-based forest fire smog feature extraction based on Pulse-Coupled neural network (PCNN) is *** PCNN is derived from the phenomena of synchronous pulse burst in mammals' visual *** outputs of PCNN represent unique features of imported images,and has been proved to be invariant to translation,rotation and *** this paper the image from video surveillance monitor is split into three dimensions in RGB color space,then input each dimension to PCNN to extract texture feature,the one-class support vector machine is applied to predict the feature in order to test feature's *** experimental results show that the algorithm we propose accurately distinguishes smog and non-smog images which outperform both the traditional Euclidean distance algorithms and the algorithms based on grey level co-occurrence matrix (GLCM) we applied in our earlier *** recognition accuracy is 98% with robustness on our smog image database.

关键词： Forest fire smog recognition,Pulse-Coupled neural network (PCNN),Support vector machine (SVM),Feature extraction,pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Robust crowd counting using detection flow

Robust crowd counting using detection flow

引用

IEEE International Conference on Image Processing

作者： Junliang Xing Haizhou Ai Liwei Liu Shihong Lao Computer Science and Technology Department Tsinghua University Beijing China Core Technology Center Omron Corporation Kyoto Japan

Crowd counting which aims at obtaining the number of people within a scene is an important computer vision task. While most previous methods try to count people within one frame, this paper addresses this problem using the detection flow which is defined as a set of object detection responses along the temporal video sequence. We argue that counting based on detection flow provides a better way to estimate the crowd size with following merits: 1) it can greatly alleviate the common weakness of an object detector including miss detection and false alarms; 2) it is robust to temporal object occlusions and noises; 3) it is more competent to give specific descriptions of the crowd, e.g. crowd moving directions and target locations. Experiment results on PETS 2009 dataset demonstrate the potential of this method.

关键词： Detectors Humans Robustness Visualization Feature extraction pattern recognition Indexes

来源：评论

学校读者我要写书评

暂无评论

Single image haze removal to deal with cross-color

Single image haze removal to deal with cross-color

引用

International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE)

作者： Guohua Zhang Taisong Jin Zhenhan Lv Lingling Li Science and technology on electro-optic control laboratory Luoyang China School of Information Science & Technology Xiamen University Xiamen China Department of Computer Science and Application Zhengzhou Institute of Aeronautical Industry Management Zhengzhou China

Single image haze removal (or de-haze) using dark channel prior model is effective when there exists a dark channel within the image. So for the images which do not meet the dark channel prior, the haze removal result may appear light pollution, cross-color. In this paper, we propose an algorithm to judge whether a single image meets the dark channel prior, and for the image that fails to meet the prior, it eliminates the cross-color influence in the image after de-hazing. Experimental results show that ours can determine whether the image meets dark channel prior, and has the better de-haze effect.

关键词： Pixel Image color analysis Helium Sparse matrices computer vision pattern recognition Conferences

来源：评论

学校读者我要写书评

暂无评论

Efficient point pattern matching algorithm for planar point sets under transform of translation, rotation and scale

引用

APPLIED MATHEMATICS AND COMPUTATION 2014年第0期232卷 624-631页

作者： Tang, Zhenjun Zhang, Xianquan Yu, Chunqiang He, Dan Guangxi Normal Univ Dept Comp Sci Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Expt Ctr Informat Sci Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin 541004 Peoples R China

Point pattern matching is an important topic in computer vision and pattern recognition, and finds many applications such as image registration, motion detection, object tracking and pose estimation. In this paper, we propose an efficient algorithm for determining correspondence between two planar point sets under transform of translation, rotation and scale. This algorithm randomly selects some points of a set and extracts their neighbor points. It views the selected points and their neighbor points as local point patterns, and finds the local matched patterns in the other set. Point pattern matching is finally achieved by counting the unique point number of those local matched point patterns with the same transform parameters. Many experiments are conducted to validate efficiency of the proposed algorithm. Running time comparisons with a well-known point pattern matching algorithm are also done and the results show that the proposed algorithm is faster than the compared algorithm. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Point pattern matching Point set matching Matched points Rotation Included angle

来源：评论

学校读者我要写书评

暂无评论

Off-line Signature Identification Using Background and Foreground Information

Off-line Signature Identification Using Background and Foreg...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Srikanta Pal Alaei Alireza Umapada Pal Michael Blumenstein School of Information and Communication Technology Griffith University Gold Coast Australia Department of Studies in Computer Science University of Mysore Mysore India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Biometric systems play an important role in the field of information security as they are extremely required for user authentication. Automatic signature recognition and verification is one of the biometric techniques, which is currently receiving renewed interest and is only one of several techniques used to verify the identities of individuals. Signatures provide a secure means for confirmation and authorization in legal documents. So nowadays, signature identification and verification becomes an essential component in automating the rapid processing of documents containing embedded signatures. In this paper, a technique for a bi-script off-line signature identification system is proposed. In the proposed signature identification system, the signatures of English and Bengali (Bangla) are considered for the identification process. Different features such as under sampled bitmaps, modified chain-code direction features and gradient features computed from both background and foreground components are employed for this purpose. Support Vector Machines (SVMs) and Nearest Neighbour (NN) techniques are considered as classifiers for signature identification in the proposed system. A database of 1554 English signatures and 1092 Bengali signatures are used to generate the experimental results. Various results based on different features are calculated and analysed. The highest accuracies of 99.41%, 98.45% and 97.75% are obtained based on the modified chain-code direction, under-sampled bitmaps and gradient features respectively using 1800 (1100 English+700 Bengali) samples for training and 846 (454 English+392 Bengali) samples for testing.

关键词： Feature extraction Support vector machines Handwriting recognition Training Educational institutions Kernel Databases

来源：评论

学校读者我要写书评

暂无评论

The marker-based watershed segmentation algorithm of ore image

The marker-based watershed segmentation algorithm of ore ima...

引用

International Conference on Communication Software and Networks, ICCSN

作者： Wei Zhang DaLing Jiang College of Electronics Information and Control Engineering Beijing University of Technology Beijing China

Image segmentation is a chief and basic issue in the field of image analysis as well as pattern recognition. Meanwhile, it is also the classical puzzle in image processing. And the watershed transform is a powerful morphological tool for image segmentation. But its short-coming is to cause over-segmentation. Therefore, labeling watershed algorithm has been presented in this paper. Firstly, a bilateral filtering is applied to smooth the original image, so it can reduce part of noise. Secondly, according to the characteristics of the ore image the distance transform and morphological reconstruction are used to realize labeling watershed transformation on this basis. Finally, segmentation result is obtained by using an improved method of labeling watershed algorithm. The experimental result shows that the method can reduce over-segmentation more efficiently, with a precision of more than 80%.

关键词： Image segmentation computer vision Shape Accuracy Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Saliency detection based on Boosting learning

Saliency detection based on Boosting learning

引用

International Conference on Computational Problem-Solving (ICCP)

作者： Xiaohu Shao Hongliang Li School of Electronic Engineering University of Science and Technology of China Chengdu China

In this paper, we propose a method for saliency detection based on Boosting algorithms in still images. Compared to saliency detectors of pixel level based, we detect salient regions of an image based on sub-windows at any locations and sizes. For each window, we compute a set of features including local contrast, gradient histogram contrast. We construct our detector based on a cascade AdaBoost classifier to get the sub-windows which contain salient objects. Generally, more than one sub-window would get through the AdaBoost detector and we introduce a score function to remove redundant sub-windows and get the final one. The algorithm is tested on the MSRA Salient Object Database, and experiment results show that the proposed approach achieves a fast and accurate saliency detection system.

关键词： Feature extraction Conferences Training computer vision Histograms pattern recognition Testing

来源：评论

学校读者我要写书评

暂无评论

Video Reshuffling with Narratives toward Effective Video Browsing

Video Reshuffling with Narratives toward Effective Video Bro...

引用

International Conference on Image and Graphics (ICIG)

作者： Wei Fu Jinqiao Wang Xiaobin Zhu Hanqing Lu Songde Ma National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China

With the rapid increasing of video cameras, large amount of video data everyday brings the problem of video storage and browsing. In this paper, we propose a novel approach to video reshuffling with a group of static images to effectively summarize the video content. Each static image called narrative is generated to depict the behavior of a specific object or a special event. Firstly background subtraction and object tracking are employed to extract the segmentations of moving objects and corresponding trajectories. After that, we apply three sampling rules to optimized select representative object samples from the spatial-temporal object tube and stitch them to the background image by Poisson blending. Experimental results show the promise of the proposed approach.

关键词： Electron tubes Histograms Trajectory Image segmentation computer vision Graphics Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Interest Points Chain (STIPC) for Activity recognition

Spatio-Temporal Interest Points Chain (STIPC) for Activity R...

引用

第一届亚洲模式识别会议

作者： Fei YUAN Veronique Prinet Gui-Song Xia Hichem Sahbi National Laboratory of Pattern Recognition Institute of Automation CAS Beijing P.R.C LTCI-CNRS TELECOM ParisTech Paris France

We present a novel feature, named Spatio-Temporal Interest Points Chain (STIPC), for activity representation and recognition. This new feature consists of a set of trackable spatio-temporal interest points, which correspond to a series of discontinuous motion among a long-term motion of an object or its part. By this chain feature, we can not only capture the discriminative motion information which space-time interest point-like feature try to pursue, but also build the connection between them. Specifically, we first extract the point trajectories from the image sequences, then partition the points on each trajectory into two kinds of different yet close related points: discontinuous motion points and continuous motion points. We extract local space-time features around discontinuous motion points and use a chain model to represent them. Furthermore, we introduce a chain descriptor to encode the temporal relationships between these interdependent local space-time features. The experimental results on challenging datasets show that our STIPC features improves local space-time features and achieve state-ofthe- art results.

关键词： Trajectory Feature extraction Tracking computer vision Humans pattern recognition Accuracy

来源：评论

学校读者我要写书评

暂无评论

Hyper-sausage coverage function neuron model and learning algorithm for image classification

引用

pattern recognition 2023年 136卷

作者： Ning, Xin Tian, Weijuan He, Feng Bai, Xiao Sun, Le Li, Weijun Chinese Acad Sci Inst Semicond Beijing 100083 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Sch Integrated Circuits Beijing 100049 Peoples R China Beijing Key Lab Semicond Neural Network Intelligen Beijing 100083 Peoples R China Yangtze Univ Dept Comp Sci Jingzhou 434023 Peoples R China Beihang Univ Jiangxi Res Inst Sch Comp Sci & Engn State Key Lab Software Dev Environm Beijing 100191 Peoples R China Cognit Comp Technol Joint Lab Wave Grp Beijing 100083 Peoples R China Nanjing Univ Informat Sci & Technol Dept Jiangsu Collaborat Innovat Ctr Atmospher Envi Nanjing 210044 Peoples R China

Recently, deep neural networks (DNNs) promote mainly by network architectures and loss functions;however, the development of neuron models has been quite limited. In this study, inspired by the mechanism of human cognition, a hyper-sausage coverage function (HSCF) neuron model possessing a high flexible plasticity. Then, a novel cross-entropy and volume-coverage (CE_VC) loss is defined, which compresses the volume of the hyper-sausage to the hilt, and helps alleviate confusion among different classes, thus ensuring the intra-class compactness of the samples. Finally, a divisive iteration method is introduced, which considers each neuron model as a weak classifier, and iteratively increases the number of weak classifiers. Thus, the optimal number of the HSCF neuron is adaptively determined and an endto-end learning framework is constructed. In particular, to improve the classification performance, the HSCF neuron can be applied to classical DNNs. Comprehensive experiments on eight datasets in several domains demonstrate the effectiveness of the proposed method. The proposed method exhibits the feasibility of boosting DNNs with neuron plasticity and provides a novel perspective for further developments in DNNs. The source code is available at https://***/Tough2011/*** .(c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://***/licenses/by/4.0/ )

关键词： pattern recognition Deep neural networks Neuron model Brain -inspired computer vision

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：