检索结果-内蒙古大学图书馆

face recognition algorithm based on feature descriptor and weighted linear sparse representation

IET IMAGE PROCESSING 2019年第12期13卷 2281-2293页

作者： Liao, Mengmeng Gu, Xiaodong Fudan Univ Dept Elect Engn Shanghai 200433 Peoples R China

Generally, the commonly used sparse-based methods, such as sparse representation classifier, have achieved a good recognition result in face recognition. However, there exist several problems in those methods. First, those methods think that the importance of each atom is the same in representing other query samples. This is not reasonable because different atoms contain different amounts of information, their importance should be different when they together represent the query samples. Second, those methods cannot meet the real-time requirement when dealing with large data set. In this study, on the one hand, the authors propose a fast extended sparse-weighted representation classifier (FESWRC) by considering the different importance of atoms and using primal augmented Lagrangian method as well as principal component analysis. On the other hand, the authors propose a distinctive feature descriptor, named logarithmic-weighted sum (LWS) feature descriptor. The authors combine FESWRC and LWS and used for face recognition, this method is called face recognition algorithm based on feature descriptor and weighted linear sparse representation (FDWLSR). Experimental results show that FDWLSR can realise real-time recognition and the recognition rate can achieve 100.0, 100.0, 91.6, 93.4 and 87.4%, respectively, on the Yale, Olivetti Research Laboratory (ORL), faculdade de engenharia industrial (FEI), face recognition technology program (FERET) and labelled face in the wild datasets.

关键词： feature extraction principal component analysis image representation face recognition distinctive feature descriptor named logarithmic-weighted sum face recognition algorithm weighted linear sparse representation real-time recognition recognition rate sparse-based methods sparse representation classifier good recognition result query samples different atoms sparse-weighted representation classifier different importance

来源：评论

学校读者我要写书评

暂无评论

face recognition algorithm using local and global information

引用

ELECTRONICS LETTERS 2002年第8期38卷 363-364页

作者： Rong, D Su, GD Lin, XG Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

A successful algorithm for the recognition of partially distorted human face images is presented, The key to this approach is to combine both local and global information. The results are compared with traditional ela... 详细信息

关键词： elastic matching algorithms global information automatic face recognition local information face recognition face recognition algorithm mismatch rate image matching Image recognition partially distorted human face images

来源：评论

学校读者我要写书评

暂无评论

A Single Training Sample face recognition algorithm Based on Sample Extension

A Single Training Sample Face Recognition Algorithm Based on...

引用

6th International Conference on Advanced Computational Intelligence (ICACI)

作者： Zhang, Erhu Li, Yongchao Zhang, Faming Xian Univ Technol Dept Informat Sci Xian 710048 Peoples R China

ISBN: (纸本)9781467363433

face recognition with single training sample has the problem that the sample is single and face pattern is changeable. The rate of traditional face recognition methods declines seriously in the case of single training sample. Thus, studying the face recognition method which is appropriate for single training sample is challenging in face recognition field. In this paper, in order to solve the problem of single training sample, sample extension method is adopted to expand fourteen virtual samples. And for the problem of changeable face pattern, like pose, expressions, illumination etc., this paper uses image blocking and applies weighted two-directional 2DPCA to extract the local feature information of face image. Further, fuse the local feature information of sub-image to face recognition. The experimental results on ORL and YALE face database show that the method in this paper achieves good recognition effect.

关键词： face recognition techniques Facial recognition subimage Functional training face recognition algorithm Laryngology local image feature face face Imagery (Psychotherapy) images

来源：评论

学校读者我要写书评

暂无评论

A GPU-paralleled implementation of an enhanced face recognition algorithm

A GPU-paralleled implementation of an enhanced face recognit...

引用

5th International Conference on Machine Vision (ICMV) - Computer Vision, Image Analysis and Processing

作者： Chen, Hao Liu, Xiyang Shao, Shuai Zan, Jiguo TCL Corp Res Xian R&D Ctr Xian Shaanxi Peoples R China Xidian Univ Inst Software Engn Xian Shaanxi Peoples R China

ISBN: (纸本)9780819495877

face recognition algorithm based on compressed sensing and sparse representation is hotly argued in these years. The scheme of this algorithm increases recognition rate as well as anti-noise capability. However, the computational cost is expensive and has become a main restricting factor for real world applications. In this paper, we introduce a GPU-accelerated hybrid variant of face recognition algorithm named parallel face recognition algorithm (pFRA). We describe here how to carry out parallel optimization design to take full advantage of many-core structure of a GPU. The pFRA is tested and compared with several other implementations under different data sample size. Finally, Our pFRA, implemented with NVIDIA GPU and Computer Unified Device Architecture (CUDA) programming model, achieves a significant speedup over the traditional CPU implementations.

关键词： GPU Parallel Computing face recognition algorithm Computer Vision

来源：评论

学校读者我要写书评

暂无评论

face recognition algorithm Bias: Performance Differences on Images of Children and Adults

Face Recognition Algorithm Bias: Performance Differences on ...

引用

IEEE/CVF Conference on Computer Vision and Pattern recognition Workshops

作者： Nisha Srinivas Karl Ricanek David S. Bolme Dana Michalski Michael King University of North Carolina Oak Ridge National Laboratory Defence Science and Technology Group Florida Institute of Technology

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

In this work, we examine if current state-of-the-art deep learning face recognition systems exhibit a negative bias (i.e., poorer performance) for children when compared to the performance obtained on adults. The systems selected for this work are five top performing~1 commercial-off-the-shelf face recognition systems, two government-off-the-shelf face recognition systems, and one open-source face recognition solution. The datasets used to evaluate the performance of the systems are both unconstrained in age, pose, illumination, and expression and are publicly available. These datasets are indicative of photo journalistic face datasets published and evaluated on, over the last few years. Our findings show a negative bias for each algorithm on children. Genuine and imposter distributions highlight the performance bias between the datasets further supporting the need for a deeper investigation into algorithm bias as a function of age cohorts. To combat the performance decline on the child demographic, several score-level fusion strategies were evaluated. This work identifies the best score-level fusion technique for the child demographic.

关键词： Child negative bias face recognition system Dataset Adults images face recognition algorithm Infant System performance Bias Statistical Biases bias(electronics) Lighting illumination

来源：评论

学校读者我要写书评

暂无评论

Optimized face recognition algorithm using Spatial and Transform Domain Techniques

Optimized Face Recognition Algorithm using Spatial and Trans...

引用

International Conference on Image Information Processing

作者： Sujatha, B. M. K. Suresh Babu Raja, K. B. Venugopal, K. R. Department of Electronics and Communication Engineering Acharya Institute of Technology Department of Electronics and Communication Engineering University Visvesvaraya College of Engineering University Visvesvaraya College of Engineering

ISBN: (纸本)9781509001491

The biometrics is used to identify or verify persons effectively in the real time scenario. In this paper, we propose Optimized face recognition algorithm using Spatial and Transform Domain Techniques. The face images are preprocessed using Discrete Wavelet Transform (DWT), resize and filtering. The Compound Local Binary Pattern (CLBP) is used to generate magnitude and sign components from preprocessed face images. The histogram is applied on sign and magnitude components of CLBP to compress number of features. The generated histogram features are concatenated to form CLBP-Histogram features. The Fast Fourier Transformation (FFT) is applied on preprocessed image and FFT magnitude features are generated. The CLBP-Histogram features are fused with FFT magnitude features to generate final feature set. The final feature sets of test image and data base images are compared using Euclidian Distance (ED) to recognise a person. It is observed that the performance parameter of the proposed algorithm is better compared to existing algorithms.

关键词： Biometrics face recognition DWT FFT CLBP Histogram Fast Fourier transform histograms Biometrics Facial recognition face recognition algorithm characteristic parameter EARTHQUAKE MAGNITUDE images Persons

来源：评论

学校读者我要写书评

暂无评论

CNN Classifier based Low-resolution face recognition algorithm

CNN Classifier based Low-resolution Face Recognition Algorit...

引用

Emerging Frontiers in Electrical and Electronic Technologies (ICEFEET), International Conference on

作者： Shyam Singh Rajput K. V. Arya National Institute of Technology Patna India ABV-Indian Institute of Information Technology & Management Gwalior India

ISBN: (数字)9781728175492

ISBN: (纸本)9781728175508

faces captured under an uncontrolled environment usually have low-resolution (LR) in addition to poor illumination conditions and uncontrolled poses. These types of images significantly deteriorate the performance of traditional face recognition techniques. Hence, in this paper, a new face recognition algorithm is developed to minimize the problem of matching the LR images with high-resolution gallery images. In the proposed algorithm, the convolutional neural network (CNN) based classification mechanism is used to improve recognition accuracy. Investigational results performed on two standard databases of face images exposes the preeminence of the proposed algorithm over the other comparative existing face recognition models.

关键词： convolutional neural nets face recognition image classification image matching image resolution image matching image resolution Facial recognition Image classification face recognition algorithm face recognition techniques images visual databases

来源：评论

学校读者我要写书评

暂无评论

Intelligence Security Check System Using face recognition algorithm: A Review

Intelligence Security Check System Using Face Recognition Al...

引用

International Conference on Electronics, Computer and Computation (ICECCO)

作者： Lateefah Abdul-azeez Abiodun Musa Aibinu Sodiq Olanrewaju Akanmu Taliha Abiodun Folorunso Momoh-Jimoh E. Salami Department of Cyber Security Science Federal University of Technology Minna Niger state Nigeria Department of Mechatronics Engineering Federal University of Technology Minna Niger state Nigeria Elizade University Ilara-Mokin Ondo State Nigeria

ISBN: (数字)9781728151601

ISBN: (纸本)9781728151618

One of the famous biometric in use is the facial recognition, which uses statistical measurement of an individual face features to discover or determine his/her identity. Human are prone to errors or mistakes, therefore, using only security personnel cannot give us a perfect security mechanism. This paper explains the importance of biometric and also present various methods which biometric application can applied in solving various problem. It focuses on face recognition and face detection techniques which include Principle Components Analysis (PCA), Hidden Markov Model (HMM), and the Discrete Wavelet Transform (DWT). It briefly explains how the use of symmetry of the face can be used for recognition, the combination of audio and video in face recognition and also show that a face can be detected in a video. It also shows the various strengths and weaknesses from each method used.

关键词： biometrics (access control) discrete wavelet transforms face recognition feature extraction hidden Markov models principal component analysis video signal processing Facial recognition discrete wavelet transform Hidden Markov models Video signal processing Feature extraction principal components analysis safety check Statistical Measurement Videotapes face recognition algorithm Security Personnel

来源：评论

学校读者我要写书评

暂无评论

A New Kernel Function Based face recognition algorithm

A New Kernel Function Based Face Recognition Algorithm

引用

2010 International Conference on Computer,Mechatronics,Control and Electronic Engineering(2010计算机、机电、控制与电子工程国际会议 CMCE 2010)

作者： JingHua Cao YanZhong Ran ZhUun Xu Department of Computer University of Ji Lin lin JiLin Province China

ISBN: (纸本)9781424479573

In general, using kernel function to solve problems of non-linear and recognition ratio, as is done in human face recognition, is particularly effectively. Firstly, a hybrid kernel function is constructed, and then a modified human face recognition algorithm about Kernel-based KICA and Kernel-based improved PSVM methods is presented. The traditional ICA methods have limitations for non-linear image in facial feature extraction process. Using kernel-based non-linear image characteristics, KICA method analyses data in the high-dimensional feature space. As a machine learning algorithm, SVM also has some limitations. This article presents an improved Nonlinear PSVM algorithm to get a better recognition ratio and a little time consuming. Eventually the tests for feasibility are performed.

关键词： face recognition algorithm KERNEL FUNCTIONS Facial recognition Kernel Extraction processes Eigenvector Machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

New perspectives in face correlation: discrimination enhancement in face recognition based on iterative algorithm 27

New perspectives in face correlation: discrimination enhance...

引用

Conference on Optical Pattern recognition XXVII

作者： Wang, Q. Alfalou, A. Brosseau, C. Guangdong Univ Technol Sch Phys & Optoelect Engn Guangzhou 510006 Guangdong Peoples R China L BISEN Vis Lab ISEN Brest 20 Rue Cuirasse BretagneCS 42807 F-29228 Brest 2 France Univ Brest Lab STICC 6 Ave Le GorgeuCS 93837 F-29238 Brest 3 France

ISBN: (纸本)9781510600867

Here, we report a brief review on the recent developments of correlation algorithms. Several implementation schemes and specific applications proposed in recent years are also given to illustrate powerful applications of these methods. Following a discussion and comparison of the implementation of these schemes, we believe that all-numerical implementation is the most practical choice for application of the correlation method because the advantages of optical processing cannot compensate the technical and/or financial cost needed for an optical implementation platform. We also present a simple iterative algorithm to optimize the training images of composite correlation filters. By making use of three or four iterations, the peak-to-correlation energy (PCE) value of correlation plane can be significantly enhanced. A simulation test using the Pointing Head Pose Image Database (PHPID) illustrates the effectiveness of this statement. Our method can be applied in many composite filters based on linear composition of training images as an optimization means.

关键词： face recognition algorithm correlation peak-to-correlation energy

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：