|Table of Contents|

Face Recognition Based on Direction-SelectedDifference Local Direction Pattern(PDF)

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2020年04期
Page:
113-118
Research Field:
·智慧应急信息技术·
Publishing date:

Info

Title:
Face Recognition Based on Direction-SelectedDifference Local Direction Pattern
Author(s):
Xu Cong; Zhu Yi; Tao Yongpeng
College of Software,Dalian University of Foreign Language,Dalian 116044,China
Keywords:
face recognition; feature extraction; Kirsch operator; local direction pattern
PACS:
TP391
DOI:
10.3969/j.issn.1001-4616.2020.04.016
Abstract:
Aiming at the problems of lack of detail and large amount of computation in feature extraction in current face recognition methods,a direction-selected difference local direction pattern was proposed. This method uses Kirsch operator to calculate the convolution value of the pixel,and performs the first adjacent difference calculation,and then selects the specific direction for the second difference calculation to generate DSDLDP mode encoding,and uses the equivalent mode to reduce the type of encoding mode.Finally,the face image is divided into multiple image blocks encoded by DSDLDP to generate corresponding histograms,which are connected in series to represent the face vector.Simulation experiment results show that compared with the current mainstream face recognition algorithms,DSDLDP algorithm extracts facial features more meticulously,with higher recognition rate,and has better robustness against noise.

References:

[1] AMIT D,ALIN D. Probabilistic characterization of nearest neighbor classifier[J]. International journal of machine learning and cybernetics,2013,4(4):259-272.
[2]HUANG D,SHAN C F,ARDABILIAN M,et al. Local binary patterns and its application to facial image analysis:a survey[J]. IEEE transactions on systems man and cybernetics,part C—applications and reviews,2011,41(6):765-781.
[3]TAN X Y,TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE transactions on image processing,2010,19(6):1635-1650.
[4]张毅,廖巧珍,罗元. 融合二阶HOG与CS-LBP的头部姿态估计[J]. 智能系统学报,2015,10(5):741-746.
[5]WANG K,BICHOT C E,LI Y,et al. Local binary circumferential and radial derivative pattern for texture classification[J]. Pattern recognition,2017,67(1):213-229.
[6]GUO Z H,LI Q,YOU J,et al. Local directional derivative pattern for rotation invariant texture classification[J]. Neural computing and applications,2012,21(8):1893-1904.
[7]JABID T,KABIR M H,CHAE O. Local Directional Pattern(LDP)for face recognition[C]//Proceedings of 2010 Digest of Technical Papers International Conference on Consumer Electronics. Las Vegas,America,2010:329-330.(2).
[8]李照奎,丁立新,王岩,等. 基于差值局部方向模式的人脸特征表示[J]. 软件学报,2015,26(11):2912-2929.
[9]王晓华,李瑞静,胡敏,等. 融合局部特征的面部遮挡表情识别[J]. 中国图象图形学报,2016,21(11):1473-1482.
[10]ISSAM E K,ABDERRAZAK C,YOUSSEF E M,,et al. Local directional ternary pattern:a new texture descriptor for texture classification[J]. Computer vision and image understanding,2018,169(1):14-27.
[11]YANG H,WANG Y D. A LBP-based face recognition method with Hamming distance constraint[C]//Fourth International Conference on Image and Graphics. Beijing,China,2007:645-649.
[12]LAJEVARDI S M,HUSSAIN Z M. Higher order orthogonal moments for invariant facial expression recognition[J]. Digital signal processing,2010,20(6):1771-1779.
[13]王玮,黄非非,李见为. 采用LBP金字塔的人脸描述与识别[J]. 计算机辅助设计与图形学学报,2009,21(1):94-100.
[14]杨恢先,刘建,张孟娟,等. 双差值局部方向模式的人脸识别[J]. 智能系统学报,2018,13(5):751-759.
[15]OJALA T,PIETIKAINEN M. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE transactions on pattern analysis and machine intelligence,2002,24(7):971-987.
[16]RAHULAMATHAVAN Y,PHANR C W,CHAMBERS J A,et al. Facial expression recognition in the encrypted domain based on local fisher discriminant analysis[J]. IEEE transactions on affective computing,2013,4(1):83-92.

Memo

Memo:
-
Last Update: 2020-11-15