位置：成果数据库 > 期刊 > 期刊详情页
基于LBP的图像集人脸识别算法
  • ISSN号：1000-1832
  • 期刊名称：《东北师大学报：自然科学版》
  • 时间：0
  • 分类：TP393[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构：吉林大学计算机科学与技术学院,吉林长春130012
  • 相关基金：国家自然科学基金资助项目（61175023）; 吉林省生物识别新技术重点实验室项目（20082209）
作者： 盖健, 刘小华, 李锐杰, 宁尚军
关键词： 人脸识别, 图像集, 仿射包, LBP, face recognition, image set, affine hull model, LBP
中文摘要：

针对基于仿射包的图像集人脸识别方法（AHISD）对于离散数据的敏感性,提出了一种加入LBP的方法.通过LBP的方法对图像进行特征提取,然后再将图像集用仿射包进行建模,在此基础上,通过计算2个模型之间的距离,以达到对人脸进行鉴别和分类的效果.用LBP方法视频数据库（Honda/UCSD）给出了检测结果,有效地提高了识别率.

英文摘要：

For affine hull face recognition based on image set（AHISD）is sensitive to outliers,this paper puts forward a new method to joint LBP with image set.Characteristics of the image are extracted by the method of LBP,and then the image set is modeled as affine model.Based on this,calculate the distance between the two models to achieve the face identification and classification.Experiments using this method in the Honda/video database show that it is effective to improve the recognition rate.

同期刊论文项目
人脸与虹膜信息融合识别新方法研究
期刊论文 61
同项目期刊论文
Incremental multi-linear discriminant analysis using canonical correlations for action recognition
一类离焦虹膜图像复原算法的研究
一种基于WordNet的短文本语义相似性算法
A Module Searching Method in Protein-protein Interaction Networks with Gene Expression Expression Pr
One new constructing multi-layer pyramid adjacency graph method for locality preserving projections
Micro-Expression Recognition Using Color Spaces
An improved k-prototypes clustering algorithm for mixed numeric and categorical data
Global and local information based spherical marginal fisher analysis for face recognition
A new construction method of neighbor graph for locality preserving projections
Building Recognition on Subregion’s Multiscale Gist Feature Extraction and Corresponding Columns Inf
基于稀疏张量的人脸图像特征提取
RSDM: A method to identify differentially expressed genes based on meta-analysis
Construction of gene regulatory network based on singular value decomposition for solution set
A study on defocused iris image restoration
Human action recognition using tensor principal component analysis
A novel algorithm for identifying protein community based on node-expand model
A novel fuzzy K-mean algorithm with fuzzy centroid for clustering mixed numeric and categorical data
Vector correction and jump out of local optimum strategy for PSO
Application of a global categorical data clustering method in medical data analysis
A fuzzy k-prototype clustering algorithm for mixed numeric and categorical data
Face recognition: a novel deep learning approach
Tensor Discriminant Analysis With Multiscale Features for Action Modeling and Categorization
Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition
Saliency Feature Enhanced Image for Face Recognition
Fold-based meta-analysis: a method for identifying differentially expressed genes in microarray data
混合属性数据聚类的新方法
基于改进的2DPCA对近红外人脸图像的识别方法
Semi-supervised discriminant analysis with tensor representation
Extensional neighborhood preserving embedding
Reconstruction of gene regulatory network based on gravitation field algorithm
A module searching method in protein-protein interaction networks with gene expression profile
A fuzzy k-prototypes algorithm using fuzzy centroid for clustering mixed data
The influence on treatment efficiency in diabetic retinopathy by laser photocoagulation area
Corresponding Block Based Graph Construction for Locality Preserving Projection
Sparse Representation-based Neighbor Graph Construction Method for Locality Preserving Projection
A General Exponential Framework for Dimensionality Reduction
Incremental Graph Regulated Nonnegative Matrix Factorization for Face Recognition
A Novel Graph Construction Method Based on Locality Sensitive Histogram for Locality Preserving Proj
基于点特异度和自适应分类策略的眼底图像分割方法
基于局部自适应点特异度阈值的眼底图像血管分割方法研究
Improving transmembrane protein consensus topology prediction using inter-helical interaction
Fusion Tensor Subspace Transformation Framework
无线链路保障QoS垂直映射技术
云平台下基因-基因相互作用识别算法
基于仿射包的图像集人脸识别的鲁棒算法
期刊信息
  • 《东北师大学报：自然科学版》
  • 北大核心期刊（2011版）
  • 主管单位:教育部
  • 主办单位:东北师范大学
  • 主编：刘宝
  • 地址：长春市净月大街2555号
  • 邮编：130117
  • 邮箱：dslkxb@nenu.edu.cn
  • 电话：0431-89165992
  • 国际标准刊号：ISSN：1000-1832
  • 国内统一刊号：ISSN：22-1123/N
  • 邮发代号:12-43
  • 获奖情况:
  • 中文综合性科学技术类核心期刊,中国科学引文数据库来源期刊,中国科技论文统计源期刊,中国期刊方阵“双效”期刊
  • 国内外数据库收录:
  • 美国化学文摘（网络版）,美国数学评论（网络版）,德国数学文摘,美国生物科学数据库,英国动物学记录,中国中国科技核心期刊,中国北大核心期刊（2004版）,中国北大核心期刊（2008版）,中国北大核心期刊（2011版）,中国北大核心期刊（2014版）,中国北大核心期刊（2000版）
  • 被引量:7830