三维掌纹局部方向特征二进制编码研究

doi:10.12263/DZXB.20190473

电子学报 ›› 2021, Vol. 49 ›› Issue (8): 1533-1540.DOI: 10.12263/DZXB.20190473

三维掌纹局部方向特征二进制编码研究

杨冰¹^,³, 莫文博², 姚金良¹^,³

^1.杭州电子科技大学计算机学院，浙江杭州 310018
^2.衢州职业技术学院信息工程学院，浙江衢州 324000
^3.浙江省脑机协同智能重点实验室，浙江杭州 310018

收稿日期:2019-04-29 修回日期:2021-02-02 出版日期:2021-08-25
- 作者简介:
- 杨冰(通信作者）女，1985年生，安徽砀山人.博士，杭州电子科技大学计算机学院副教授，硕士生导师.主要从事模式识别、计算机视觉研究. E-mail:yb@hdu.edu.cn
  莫文博男，1994年生，吉林通化人.硕士，衢州职业技术学院信息工程学院教师，主要从事掌纹识别、图像处理研究.
- 基金资助:
- 国家自然科学基金 (U1909202); 浙江省省属高校基本科研业务费专项资金 (GK209907299001-008)

Learning Local Direction Binary Code for 3D Palmprint

YANG Bing¹^,³, MO Wen-bo², YAO Jin-liang¹^,³

^1.School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China
^2.Information Engineering School, Quzhou College of Technology, Quhou, Zhejiang 324000, China
^3.Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, Zhejiang 310018, China

Received:2019-04-29 Revised:2021-02-02 Online:2021-08-25 Published:2021-08-25
- Supported by:
- National Natural Science Foundation of China (U1909202); Fundamental Research Funds for Provincial Colleges and Universities of Henan Province (GK209907299001-008)

摘要/Abstract

摘要：

三维掌纹能显著地减少应用过程中潜在的安全隐患，近年来吸引了越来越多的关注.然而，现有的三维掌纹识别方法大多借助人工设计的描述符来进行匹配，这往往需要先验知识.本文提出一种基于学习策略的局部方向特征二进制编码来完成三维掌纹识别.该方法利用形状指数来描述三维掌纹的局部几何特征，并且在形状指数图像上计算Gabor滤波器响应并将响应差值组合起来形成特征向量.提出利用哈希学习模型得到特征映射函数并将响应差值特征向量转换为方向特征二进制编码，并对方向特征二进制编码图采用分块策略形成特征直方图来进行匹配.在香港理工三维掌纹数据库上的实验结果表明，本文方法在识别率上要优于目前流行的其他三维掌纹识别方法，从而验证了本文方法的有效性.

关键词: 三维掌纹识别, 局部方向特征二进制编码, 形状指数, 哈希学习

Abstract:

Three dimensional (3D) palmprint could efficiently reduce potential security risks in practical applications, and thus attracts a growing interest in recent years. However, most existing 3D palmprint recognition methods require hand-craft designed descriptors and strong prior knowledge are needed. In this paper, we propose a local direction binary code learning method for 3D palmprint recognition. We employ shape index representation to demonstrate the geometry characteristics of local regions in 3D palmprint data, and form Gabor filter response difference vector as the feature vectors by applying the Gabor filter on the shape index image. We utilize the hash learning model to learn feature mapping functions that can project these feature vectors into direction binary code, and further construct the block-wise histograms for matching. Experiments on Hong Kong Polytechnic University 3D palmprint database validate that our method outperforms existing state-of-the-art methods in terms of recognition accuracy, showing the effectiveness of our method.

Key words: 3D palmprint recognition, local direction binary code, shape index, hash learning

中图分类号:

TP391.4

杨冰, 莫文博, 姚金良. 三维掌纹局部方向特征二进制编码研究[J]. 电子学报, 2021, 49(8): 1533-1540.

Bing YANG, Wen-bo MO, Jin-liang YAO . Learning Local Direction Binary Code for 3D Palmprint[J]. Acta Electronica Sinica, 2021, 49(8): 1533-1540.

图/表 10

图1 本文方法流程图

图2 形状指数图示例

图3 Gabor滤波器响应差值向量产生过程示意图

图4 基于方向二进制编码描述符的三维掌纹识别流程图(a)训练样本；(b)学习得到的投影矩阵；(c)测试样本；(d)二进制编码特征谱；(e)二进制编码描述符

表1 不同训练样本条件下，三维掌纹识别方法识别率比较表

方法	N=2	N=4	N=10
文献［12］	0.9269	0.9610	0.9843
文献［13］	0.9417	0.9726	0.9915
文献［14］	0.9731	0.9952	0.9966
本文方法	0.9840	0.9955	0.9967

表2 识别率随权重参数λ取值变化表

	$λ$ =0.01	$λ$ =0.1	$λ$ =1	$λ$ =10	$λ$ =100
N=2	0.9795	0.9813	0.9840	0.9803	0.9806
N=4	0.9914	0.9931	0.9955	0.9926	0.9902

表2 识别率随权重参数λ取值变化表

	$λ$ =0.01	$λ$ =0.1	$λ$ =1	$λ$ =10	$λ$ =100
N=2	0.9795	0.9813	0.9840	0.9803	0.9806
N=4	0.9914	0.9931	0.9955	0.9926	0.9902

图5 识别率随投影矩阵大小M变化图

表3 识别率随分块大小变化表

8像素×

8像素

16像素×

16像素

24像素×

24像素

32像素×

32像素

表4 三维掌纹鉴别实验比较表

方法	FAR=0.001	FAR=0.1
文献［12］	0.8312	0.9287
文献［14］	0.8756	0.9725
本文方法	0.8914	0.9827

表5 各种方法平均特征提取与匹配时间比较表/s

方法	特征提取	匹配
文献［12］	0.0139	0.0071
文献［13］	0.0165	/
文献［14］	0.0254	0.0174
本文方法	0.0262	0.0027

参考文献 20

1	Arteaga-FalconiJ S, OsmanH A, SaddikA E. ECG authentication for mobile devices[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(3): 591-600.
2	XuY, FeiL, ZhangD. Combining left and right palmprint images for more accurate personal identification[J]. IEEE Transactions on Image Processing, 2015, 24(2): 549-559.
3	孙冬梅, 裘正定. 生物特征识别技术综述[J]. 电子学报, 2001, 29(S1): 1744-1748.
	SunD M, QiuZ D. A survey of the emerging biometric technology[J]. Acta Electronica Sinica, 2001, 29(S1): 1744-1748. (in Chinese)
4	李强, 裘正定, 孙冬梅, 等. 基于改进二维主成分分析的在线掌纹识别[J]. 电子学报, 2005, 33(10): 1886-1889.
	LiQ, QiuZ D, SunD M, et al. Online palmprint identification based on improved 2D PCA[J]. Acta Electronica Sinica, 2005, 33(10): 1886-1889. (in Chinese)
5	LiuD, SunD, QiuZ. A novel image enhancement method for SIFT feature extraction of low resolution palmprint images[J]. Chinese Journal of Electronics, 2011, 20(1): 111-113.
6	FeiL, XuY, TangW, et al. Double-orientation code and nonlinear matching scheme for palmprint recognition[J]. Pattern Recognition, 2016, 49: 89-101.
7	HaoF, ChangX, YangG, et al. Local image quality measurement for multi-scale forensic palmprints[J]. Multimedia Tools and Applications, 2020, 79(19): 12915-12938.
8	HaoF, YangL, YangG, et al. RFPIQM: Ridge-based forensic palmprint image quality measurement[J]. IEEE Access, 2018, 6: 62076-62088.
9	ZhengQ, KumarA, PanG. A 3D feature descriptor recovered from a single 2D palmprint image[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(6): 1272-1279.
10	白雪飞, 高楠, 张宗华, 等. 基于分块ST与主成分分析的三维掌纹识别[J]. 天津大学学报(自然科学与工程技术版), 2018, 51(6): 631-637.
	BaiX F, GaoN, ZhangZ H, et al. Three dimensional palmprint identification based on blocked ST and PCA[J]. Journal of Tianjin University (Science and Technology), 2018, 51(6): 631-637. (in Chinese)
11	YangB, XiangX, XuD, et al. 3D palmprint recognition using shape index representation and fragile bits[J]. Multimedia Tools and Applications, 2017, 76(14): 15357-15375.
12	LiW, ZhangD, ZhangL, et al. 3D palmprint recognition with joint line and orientation features[J]. IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews, 2011, 42(2): 274-279.
13	ZhangL, ShenY, LiH, et al. 3D palmprint identification using block-wise features and collaborative representation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(8): 1730-1736.
14	FeiL, ZhangB, XuY, et al. Precision direction and compact surface type representation for 3D palmprint identification[J]. Pattern Recognition, 2019, 87(3): 237-247.
15	FeiL, LuG, JiaW, et al. Feature extraction methods for palmprint recognition: A survey and evaluation[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(2): 346-363.
16	LiW, ZhangD, LuG, et al. A novel 3D palmprint acquisition system[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 2012, 42(2): 443-452.
17	HetzelG, LeibeB, LeviP, et al. 3D Object Recognition from Range Images using Local Feature Histograms[A]. Proceedings of the 14nd IEEE International Conference on Computer Vision and Pattern Recognition[C]. Washington, USA: IEEE Computer Society Press, 2001. 394-399.
18	WangJ, ZhangT, SongJ, et al. A survey on learning to hash[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 769-790.
19	WuX, ZhangD, WangK. Fisherpalms based palmprint recognition[J]. Pattern Recognition Letter, 2003, 24(15): 2829-2838.
20	LuJ, LiongV, ZhouJ. Simultaneous local binary feature learning and encoding for homogeneous and heterogeneous face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(8): 1979-1993.

三维掌纹局部方向特征二进制编码研究

Learning Local Direction Binary Code for 3D Palmprint

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 20

相关文章 1

编辑推荐

Metrics