Image restoration of finger-vein networks based on encoder-decoder model

Abstract

Finger-vein recognition is widely applied on access control system due to the high user acceptance and convince. Improving the integrity of finger-vein is helpful for increasing the finger-vein recognition accuracy. During the process of finger-vein imaging, foreign objects may be attached on fingers, which directly affects the integrity of finger-vein images. In order to effectively extract finger-vein networks, the integrity of venous networks is still not ideal after preprocessing of finger vein images. In this paper, we propose a novel deep learning based image restoration method to improve the integrity of finger-vein networks. First, a region detecting method based on adaptive threshold is presented to locate the incomplete region. Next, an encoder-decoder model is used to restore the venous networks of the finger-vein images. Then we analyze the restoration results using several different methods. Experimental results show that the proposed method is effective to restore the venous networks of the finger-vein images.

References

[1] MiuraN, NagasakaA, MiyatakeT. Machine Vision and Applications, 2004, 15: 194

[2] YangJ-f, YangJ-l, ShiY-h. Computers in Human Behavior, 2011, 27: 5

[3] YangJ-f, YangJ-l, ShiY-h. Combination of Gabor Wavelets and Circular Gabor Filter for Finger-Vein Extraction, International Conference on Intelligent Computing, 2009, 346

[4] LeeE, LeeH, ParkK. Imaging Systems and Technology, 2009, 19: 175

[5] YangJ-f, ShiY-h. Information Sciences, 2014, 268: 33

[6] YangJ-f, ShiY-h. Pattern Recognition Letters, 2012, 33: 12

[7] MeiC-l X X, LiuG-h, ChenY, LiQ-A. Fuzzy Systems and Knowledge Discovery, 2009, 3: 407

[8] PathakD, KrahenbuhlP, DonahueJ, DarrellT, EfrosA. Context Encoders: Feature Learning by Inpainting, IEEE Conference on Computer Vision and Pattern Recognition, 2016, 2536

[9] YangC, LuX, LinZ, ShechtmanE, WangO, LiH. High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis, IEEE Conference on Computer Vision and Pattern Recognition, 2017, 4076

[10] YuJ-h, LinZ, YangJ-m, ShenX-h, LuX, HuangT. Generative Image Inpainting with Contextual Attention, IEEE Conference on Computer Vision and Pattern Recognition, 2018, 5505