检索结果-内蒙古大学图书馆

Face recognition using skin color segmentation and template matching algorithms

Information Technology Journal 2011年第12期10卷 2308-2314页

作者： Wang, Zhiwen Li, Shaozi Department of Computer and Engineering Guangxi University of Technology Liuzhou China Department of Cognitive Science Xiamen University Xiamen China Key Laboratory of the Brain-Like Intelligent Systems Xiamen University Xiamen China

Currently, relatively popular and representative face recognition algorithms are algorithm based on template matching and algorithms based on skin-color segmentation. The computation of recognition algorithm based on template matching is very high and the recognition rate of recognition algorithms based on skin color segmentation is low and is vulnerable to the impact of background which is similar with skin color, In order to overcome these deficiencies, face recognition using skin color segmentation and template matching algorithm is presented in this study. According to the clustering properties that the skin-color of human faces emerge in the YCbCr color space, the regions closing to facial skin color are separated from the image by using Gaussian mixture model in order to achieve the purpose of rapidly detecting the external face of human face. Adaptive template matching is used to overcome the affect of the backgrounds which are similar with skin color on face detection and recognition. Computation in the matching process is reduced by using the second matching algorithm. Extraction of face images by using singular value features is used to identify faces and to reduce the dimensions of the eigenvalue matrix in the process of facial feature extraction. Experimental results show that proposed method can rapidly detect and recongnise human faces and improve the accuracy of face detection and recognition. © 2011 Asian Network for Scientific Information.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A probabilistic approach to spatio-spectral filters optimization in brain-computer Interface

A probabilistic approach to spatio-spectral filters optimiza...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Heung-Il Suk Seong-Whan Lee Department of Computer Science and Engineering Korea University Anam-dong Seongbuk-ku Seoul Korea Department of Brain and Cognitive Engineering Korea University Anam-dong Seongbuk-ku Seoul Korea

EEG-based motor imagery classification has been widely studied for brain-computer Interfaces (BCIs) due to its asynchronous and continuous elicitation and its great potential to many applications. Many research groups have devoted their efforts to either the frequency band selection or optimal spatial filters learning via the Common Spatial Pattern (CSP) algorithm. However, since the spectral filtering and the spatial filtering are generally operated in order in a motor imagery classification system the optimization of the spatial filters and the spectral filters should be considered simultaneously in a unified framework. In this paper, we propose a novel probabilistic approach for the spatio-spectral filters optimization in an EEG-based BCI with a particle-filter algorithm and mutual information between feature vectors and class labels. There are two main contributions of the proposed method. The one is that it finds the optimal frequency bands that maximally discriminate the feature vectors of two classes in terms of an information theoretic approach. The other is that we construct a spectrally-weighted label decision rule by linearly combining the outputs from multiple SVMs, one for each frequency band, with the weight of the corresponding frequency band. From our experiments with two publicly available dataset, we confirm that the proposed method outperforms the other competing methods.

关键词： Electroencephalography Feature extraction Vectors Optimization Entropy Mutual information Training

来源：评论

学校读者我要写书评

暂无评论

The integration of skin color segmentation and self-adapted template matching for the robust face detection

引用

International Review on computers and Software 2011年第5期6卷 795-805页

作者： Zhiwen, Wang Shao-Zi, Li Ying, Dai Cognitive Science Department Xiamen University Xiamen 361005 China Department of Computer and Engineering Guangxi University of Technology Liuzhou 545006 China Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University Xiamen 361005 China Faculty of Software and Info. Science Iwate Pref. University Iwate Japan

In this paper, an approach of integrating skin color segmentation and self-adapted template matching for the robust face detection is proposed. According to the clustering properties of the skin color of human faces in the YCbCr color space, the regions which close to the skin color are separated from the image by using Gaussian mixture model in order to achieve the purpose of rapidly detecting the external face. The influence of the brightness on the detection of the human faces is eliminated by using the illumination compensation technology, and also the confusion of the regions with the closed skin color with the human face is overcome by the adaptive template matching. Computation in the matching process is reduced by using the second matching algorithm. Experimental results show that proposed method can rapidly detect the human faces from a variety of images, while those detected faces include several of facial images with the different sizes, poses, races under the different illumination conditions. © 2011 Praise Worthy Prize S.r.l. - All rights reserved.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

AdaBoost for Text Detection in Natural Scene

AdaBoost for Text Detection in Natural Scene

引用

International Conference on Document Analysis and Recognition

作者： Jung-Jin Lee Pyoung-Hean Lee Seong-Whan Lee Alan Yuille Christof Koch Department of Brain and Cognitive Engineering Korea University Seoul South Korea Departments of Statistics Psychology Computer Science UCLA Los Angeles CA USA Computation and Neural Systems California Institute of Technology Pasadena CA USA

Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.

关键词： Feature extraction Image edge detection Image color analysis Algorithm design and analysis Histograms Optimization Energy measurement

来源：评论

学校读者我要写书评

暂无评论

A wirelessly powered and controlled device for optical neural control of freely-behaving animals

A wirelessly powered and controlled device for optical neura...

引用

作者： Wentz, Christian T. Bernstein, Jacob G. Monahan, Patrick Guerra, Alexander Rodriguez, Alex Boyden, Edward S. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology 77 Massachusetts Ave Cambridge MA 02139 United States McGovern Institute for Brain Research Massachusetts Institute of Technology 77 Massachusetts Ave Cambridge MA 02139 United States Media Lab. Massachusetts Institute of Technology 77 Massachusetts Ave Cambridge MA 02139 United States Department of Brain and Cognitive Sciences Massachusetts Institute of Technology 77 Massachusetts Ave Cambridge MA 02139 United States Department of Biological Engineering Massachusetts Institute of Technology 77 Massachusetts Ave Cambridge MA 02139 United States

Optogenetics, the ability to use light to activate and silence specific neuron types within neural networks in vivo and in vitro, is revolutionizing neuroscientists' capacity to understand how defined neural circuit elements contribute to normal and pathological brain functions. Typically, awake behaving experiments are conducted by inserting an optical fiber into the brain, tethered to a remote laser, or by utilizing an implanted light-emitting diode (LED), tethered to a remote power source. A fully wireless system would enable chronic or longitudinal experiments where long duration tethering is impractical, and would also support high-throughput experimentation. However, the high power requirements of light sources (LEDs, lasers), especially in the context of the extended illumination periods often desired in experiments, precludes battery-powered approaches from being widely applicable. We have developed a headborne device weighing 2 g capable of wirelessly receiving power using a resonant RF power link and storing the energy in an adaptive supercapacitor circuit, which can algorithmically control one or more headborne LEDs via a microcontroller. The device can deliver approximately 2 W of power to the LEDs in steady state, and 4.3 W in bursts. We also present an optional radio transceiver module (1 g) which, when added to the base headborne device, enables real-time updating of light delivery protocols;dozens of devices can be controlled simultaneously from one computer. We demonstrate use of the technology to wirelessly drive cortical control of movement in mice. These devices may serve as prototypes for clinical ultra-precise neural prosthetics that use light as the modality of biological control. © 2011 IOP Publishing Ltd.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

A compositional approach to learning part-based models of objects

A compositional approach to learning part-based models of ob...

引用

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Roozbeh Mottaghi Ananth Ranganathan Alan Yuille Department of Computer Science University of California Los Angeles USA Honda Research Institute USA Inc. Mountain View CA USA Department of Brain and Cognitive Engineering Korea University Seoul South Korea Department of Statistics University of California Los Angeles USA

We propose a new method for learning probabilistic part-based models of objects using only a limited number of positive examples. The parts correspond to HOG bundles, which are groupings of HOG features. Each part model is supplemented by an appearance model, which captures the global appearance of the object by using bags of words of PHOW features. The learning is invariant to scaling and in-plane rotations of the object, the number of parts is learnt automatically, and multiple models can be learnt to allow for variations of 3D viewpoint or appearance. Through an experiment, we show that 3D multi-view object recognition can be performed by a series of learnt 2D models. The method is supervised but can learn models for multiple object viewpoints without these viewpoints being labeled in the training data. We evaluate our method on three benchmark datasets: (i) the ETHZ shape dataset, (ii) the INRIA horse dataset, and (iii) a multiple viewpoint car dataset. Our results on these datasets show proof of concept for our approach since they are superior or close to the state-of-the-art on all three datasets while we do not use any negative examples.

关键词： Mathematical model Data models Computational modeling Solid modeling Equations Three dimensional displays Vectors

来源：评论

学校读者我要写书评

暂无评论

Towards optogenetic sensory replacement

Towards optogenetic sensory replacement

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： M. Mehdi Doroudchi Kenneth P. Greenberg Anthony N. Zorzos William W. Hauswirth Clifton G. Fonstad Alan Horsager Edward S. Boyden Eos Neuroscience Inc. Los Angeles CA USA Division of Neurobiology University of California Berkeley Berkeley CA USA MIT Media Laboratory Synthetic Neurobiology Group Departments of Brain and Cognitive Sciences and Biological Engineering MIT McGovern Institute MIT Microsystems Technology Laboratory MIT Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Ophthalmology University of Florida Gainesville FL USA MIT Microsystems Technology Laboratory MIT Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Institute for Genetic Medicine University of Southern California (USC) Los Angeles CA USA Media Laboratory McGovern Institute and Departments of Brain and Cognitive Sciences and Biological Engineering Massachusetts Institute of Technology Cambridge MA USA

Over the last several years we have developed a rapidly-expanding suite of genetically-encoded reagents (e.g., ChR2, Halo, Arch, Mac, and others) that, when expressed in specific neuron types in the nervous system, enable their activities to be powerfully and precisely activated and silenced in response to light. If the genes that encode for these reagents can be delivered to cells in the body using gene therapy methods, and if the resultant protein payloads operate safely and effectively over therapeutically important periods of time, these molecules could subserve a set of precise prosthetics that use light as the trigger of information entry into the nervous system, e.g. for sensory replacement. Here we discuss the use of ChR2 to make the photoreceptor-deprived retina, as found in diseases such as retinitis pigmentosa, sensitive to light, enabling restoration of functional vision in a mouse model of blindness. We also discuss arrays of light sources that could be useful for delivering patterned sensory information into the nervous system.

关键词： Optical waveguides Probes Neurons Neuroscience Blindness Mice Retina

来源：评论

学校读者我要写书评

暂无评论

Computational models of narrative: Review of the workshop

引用

AI Magazine 2010年第2期31卷 97-100页

作者： Finlayson, Mark A. Richards, Whitman Winston, Patrick H. Electrical Engineering and Computer Science Massachusetts Institute of Technology United States Department of Brain and Cognitive Sciences Massachusetts Institute of Technology United States Department of Cognitive Science Media Arts and Sciences MIT Media Lab United States Department of Artificial Intelligence and Computer Science MIT United States MIT Artificial Intelligence Laboratory United States

On October 8-10,2009, an interdisciplinary group met in Beverley, Massachusetts, to evaluate the state of the art in the computational modeling of narrative. Three important findings emerged: (1) current work in computational modeling is described by three different levels of representation;(2) there is a paucity of studies at the highest, most abstract level aimed at inferring the meaning or message of the narrative;and (3) there is a need to establish a standard data bank of annotated narratives, analogous to the Penn Treebank. Copyright © 2010, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Structured local binary Haar pattern for graphics retrieval

Structured local binary Haar pattern for graphics retrieval

引用

2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010

作者： Su, Song-Zhi Chen, Shu-Yuan Li, Shang-An Li, Shao-Zi Duh, Der-Jyh Cognitive Science Department Xiamen University Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen China Department of Computer Engineering and Science Yuan-Ze University Taiwan Department of Computer Science and Information Engineering Ching-Yun University Taiwan

ISBN: (纸本)9781424465835

Feature extraction is an important issue in graphics retrieval. Local feature based descriptors are currently the predominate method used in image retrieval and object recognition. Inspired by the success of Haar feature and Local Binary Pattern (LBP), a novel feature named structured local binary Haar pattern (SLBHP) is proposed for graphics retrieval in this paper. SLBHP encodes the polarity instead of the magnitude of the difference between accumulated gray values of adjacent rectangles. Experimental results on graphics retrieval show that the discriminative power of SLBHP is better than those of using edge points (EP), Haar feature, and LBP even in noisy condition. ©2010 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Robust sign language recognition with hierarchical conditional random fields

Robust sign language recognition with hierarchical condition...

引用

International Conference on Pattern Recognition

作者： Yang, Hee-Deok Lee, Seong-Whan School of Computer Engineering Chosun University Gwangu Korea Republic of Department of Computer Science and Engineering Dpartment of Brain and Cognitive Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9780769541099

Sign language spotting is the task of detection and recognition of signs (words in the predefined vocabulary) and fingerspellings (a combination of continuous alphabets that are not found in signs) in a signed utterance. The internal structures of signs and fingerspellings differ significantly. Therefore, it is difficult to spot signs and fingerspellings simultaneously. In this paper, a novel method for spotting signs and fingerspellings is proposed, which can distinguish signs, fingerspellings, and nonsign patterns. This is achieved through a hierarchical framework consisting of three steps;(1) Candidate segments of signs and fingerspellings are discriminated with a two-layer conditional random field (CRF). (2) Hand shapes of detected signs and fingerspellings are verified by BoostMap embeddings. (3) The motions of fingerspellings are verified in order to distinguish those which have similar hand shapes and differ only in hand trajectories. Experiments demonstrate that the proposed method can spot signs and fingerspellings from utterance data at rates of 83% and 78%, respectively. © 2010 IEEE.

关键词： Random processes

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：