Finger vein recognition algorithm based on FAST feature extraction

被引：0

作者：

Li W.-J. ^{[1
,2
]}

Jing J. ^{[1
,2
]}

Di S. ^{[1
,2
]}

机构：

[1] Precision Engineering Research Center, Guangzhou Institute of Advanced Technology, Chinese Academy of Sciences, Guangzhou

[2] College of Information Science and Technology, Chengdu University of Technology, Chengdu

来源：

Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2020年 / 28卷 / 02期

关键词：

Corner detection; Feature point description; Finger vein recognition; Matching distance;

D O I：

10.3788/OPE.20202802.0507

中图分类号：

学科分类号：

摘要：

Finger vein recognition algorithms are usually based on grayscale images of vein distributions. However, because of the limitations of image acquisition devices, the uncertainties in the illumination intensity and the complexity of the tissue around the finger vessels (among other factors)even after image processing cause the resulting grayscale images to possess irregular shadows and non-venous characteristics, which may reduce the accuracy of the recognition results. Therefore, this paper proposed a new finger vein identification algorithm based on binary images to minimize the interference of non-venous factors in the identification process. First, the features from accelerated segment test algorithm was used to extract the pixel points at the edges of vein textures as feature points, and then the feature vectors were constructed. Further, to improve the matching precision, a new matching algorithm based on circular neighborhoods was proposed. The weighted matching distance was used to describe the degree of similarity between images. The average recognition rate of the proposed method when applied to the finger vein database published by Shandong University is 0.993, and the equal error rate is 0.019 6.These results demonstrate the effectiveness of the algorithm and provide a new basis for the design of vein recognition algorithms. © 2020, Science Press. All right reserved.

引用

页码：507 / 514

页数：7

共 19 条

[1]

Cheng Y., Chen H., Cheng B., Et al., Special point representations for reducing data space requirements of finger-vein recognition applications, Multimedia Tools and Applications, 76, 9, pp. 11251-11271, (2017)

[2]

Rosdi B.A., Shing C.W., Suandi S.A., Et al., Finger vein recognition using local line binary pattern, Sensors, 11, 12, pp. 11357-11371, (2011)

[3]

Lee E.C., Jung H., Kim D., Et al., New finger biometric method using near infrared imaging, Sensors, 11, 3, pp. 2319-2333, (2011)

[4]

Song W., Kim T., Kim H.C., Et al., A finger-vein verification system using mean curvature, Pattern Recognition Letters, 32, 11, pp. 1541-1547, (2011)

[5]

Cui J.J., Li Q., Xue D.Y., Finger vein image deblurring method based on skin scattering models, Opt. Precision Eng., 24, 10, pp. 727-732, (2016)

[6]

Matsuda Y., Miura N., Nagasaka A., Et al., Finger-vein authentication based on deformation-tolerant feature-point matching, Machine Vision and Applications, 27, 2, pp. 237-250, (2016)

[7]

William A., Ong T.S., Lau S.H., Et al., Finger vein verification using local histogram of hybrid texture descriptors, 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 304-308, (2015)

[8]

Cui J., Xie J., Liu T., Et al., Corners detection on finger vein images using the improved Harris algorithm, Optik, 125, 17, pp. 4668-4671, (2014)

[9]

Meng X.J., Xi X.M., Yang L., Et al., Finger vein recognition based on intensity inhomogeneity correction and scale invariant feature transform, Journal of Nanjing University(Natural Science), 54, 238, pp. 7-16, (2018)

[10]

Kanopoulos N., Vasanthavada N., Baker R.L., Et al., Design of an image edge detection filter using the Sobel operator, IEEE Journal of Solid-state Circuits, 23, 2, pp. 358-367, (1988)

← 1 2 →