浏览全部资源
扫码关注微信
Received：29 June 2023，
Revised：2023-12-16，
Published：16 September 2024
移动端阅览
目的
2
基于手掌静脉的身份识别需要在近红外光下采集手掌血管图像，安全性高。开放环境下的非接触式采集，相对于传统的将手掌放到采集箱体内固定栓上的采集方式更受用户欢迎。但开放环境带来的可见光干扰和非接触拍摄带来的图像旋转、平移、比例缩放、光照改变使得识别具有挑战性。针对以上两个难点，研究了一种基于非监督卷积神经网络的方法。
方法
2
在卷积层中结合主成分分析（principal component analysis，PCA）滤波器提取主元信息，减少由于可见光引起的噪声影响；以固定尺寸Gabor滤波器为多尺度自适应Gabor滤波器提供先验知识，克服图像因几何与光照改变对识别产生的干扰，用以增强掌脉稳定特征，提升识别性能，再以二值化方式降低数据量，最后使用自适应K近邻（K-nearest neighbors，KNN）的变体分类器进行分类识别。
结果
2
采用自建图库、同济图库和PolyU-NIR图库进行实验分析，在3个图库中的等误率分别为0.289 9%、0.211 3%和0.158 6%，误拒率和误识率分别为0.002 7和2.318 8、0.002 3和1.282 1、0.000 0和1.596 2。
结论
2
与传统方法以及经典网络方法相比，该方法能有效提高识别准确率，适用于对安全性要求较高的场合进行身份识别，具有实用价值。
Objective
2
Palm vein recognition takes advantage the stability and uniqueness of human palm vein distribution for identification. The palm vein is hidden under the epidermis and cannot be photographed under visible light， and the replication of its complex structure presents difficulty. A severed palm or corpse fails certification because blood has stopped flowing， which makes palm vein recognition suitable for high-security applications. The noncontact collection in an open environment is more popular than the traditional collection method of placing the palm on a fixed bolt in the collection box. However， the opacity， inhomogeneity， and anisotropy of the skin tissue covering the palm vein cause scattering of near-infrared light. The visible light in open environments aggravates scattering and increases noise， which result in vague palm vein imaging in some people. The noncontact acquisition method increases the intraclass difference of the same sample increase due to rotation， translation， scaling， and illumination in multiple shots. The above difficulties make recognition challenging. A method based on unsupervised convolutional neural network was studied with aim of addressing such difficulties.
Method
2
Given that this paper requires a benchmark library to train the self-built network， a palm vein image library containing 600 images from 100 volunteers was established. Then， the program parameters were trained and adjusted using the self-built library. After several training adjustments， the optimal \and the trained network parameters were acquired. In image preprocessing， the region of interest （ROI） was extracted from all the palm vein images collected. First， the original palm vein image was denoised and binarized via low-pass filtering. Then， the palm contour was extracted via the dilation method in binary morphology. The obtained palm contour was refined into a single pixel， and the palm vein ROI was extracted using a method mentioned in literature. The extracted palm-vein ROI was adjusted based on the corresponding pixel size， and the mean was subtracted for normalization. A local region was extracted for each pixel in the processed ROI of the palm vein to ensure that it covers the entire ROI of the palm vein. In addition， all local regions are converted into vector forms. A filter of the principal component analysis was used to extract principal component information in the convolution layer to reduce the noise caused by visible light. The fixed-size Gabor filter was used to obtain prior knowledge on the multiscale adaptive Gabor filter to overcome the interferences resulting from image rotation， translation， scaling， and illumination changes on recognition and improve palm-vein stability features and recognition performance. Then， the amount of data was reduced by binarization. Finally， the adaptive K-nearest neighbors （Ada-KNN） variant classifier was used for classification and recognition. The Ada-KNN2 classifier uses heuristic learning method instead of neural network. With the use of density and distribution of the test point neighborhood， the specific k value suitable for the test point was determined using an artificial neural network to achieve efficient and accurate distinction between samples and solve the problem of the increased difference in the same sample image. In addition， unbalanced sample data are avoided， which a great influence on the results.
Result
2
Experimental findings show that this method can effectively increase the recognition accuracy compared with traditional and classical network methods. The equal error rates （EERs） of the three libraries were 0.289 9%， 0.211 3%， and 0.158 6%， respectively. Compared with the traditional method that had the best effect on the three libraries during comparison， EER was reduced by 0.176 8%， 2.466 5%， and 1.468 1% compared with the classical network method that had the best effect. EER decreased by 0.033 3%， 0.233 3%， and 0.248 7%. The false rejection rate/false accept rate were 0.002 7/2.318 8， 0.002 3/1.282 1， and 0.000 0/1.596 2. In addition， from the generated receiver operating characteristic curve， the advantages of the method in recognition performance can be observed more intuitively. It can distinguish and recognize similar images to a great extent and improve the overall recognition performance. The proposed method also effectively solves the problem of increased differences in similar images due to alterations in rotation， translation， scaling， and illumination during noncontact acquisition， which led to a decrease in the recognition performance.
Conclusion
2
The experimental findings underscore the effectiveness of the proposed method in addressing the aforementioned challenges. Nevertheless， the operational efficiency of this approach exhibits relative insufficiency. Consequently， further investigation and in-depth studies should be aimed at addressing this efficiency gap. Future research endeavors should cover strategies for the systematic enhancement of the operational efficiency without compromising the robustness and precision of the recognition process. One pivotal area of exploration pertains to sample size expansion， which warrants a meticulous examination of methodologies to ensure the scalability of the proposed approach. Concurrently， optimization measures should be meticulously devised to fine tune operational aspects to achieve an optimal balance between efficiency and accuracy.
Almaghtuf J ， Khelifi F and Bouridane A . 2020 . Fast and efficient difference of block means code for palmprint recognition . Machine Vision and Applications ， 31 （ 6 ）： # 51 ［ DOI： 10.1007/s00138-020-01103-3 http://dx.doi.org/10.1007/s00138-020-01103-3 ］
Babalola F O ， Bitirim Y and Toygar Ö . 2021 . Palm vein recognition through fusion of texture-based and CNN-based methods . Signal， Image and Video Processing ， 15 （ 3 ）： 459 - 466 ［ DOI： 10.1007/s11760-020-01765-6 http://dx.doi.org/10.1007/s11760-020-01765-6 ］
Bansal M ， Kumar M and Kumar M . 2021 . 2D object recognition： a comparative analysis of SIFT， SURF and ORB feature descriptors . Multimedia Tools and Applications ， 80 （ 12 ）： 18839 - 18857 ［ DOI： 10.1007/S11042-021-10646-0 http://dx.doi.org/10.1007/S11042-021-10646-0 ］
Bhatnagar J and Kumar A . 2009 . On estimating performance indices for biometric identification . Pattern Recognition ， 42 （ 9 ）： 1803 - 1815 ［ DOI： 10.1016/j.patcog.2008.10.004 http://dx.doi.org/10.1016/j.patcog.2008.10.004 ］
Chan T H ， Jia K ， Gao S H ， Lu J W ， Zeng Z N and Ma Y . 2015 . PCANet： a simple deep learning baseline for image classification？ IEEE Transactions on Image Processing ， 24 （ 12 ）： 5017 - 5032 ［ DOI： 10.1109/TIP.2015.2475625 http://dx.doi.org/10.1109/TIP.2015.2475625 ］
Fei L K ， Lu G M ， Jia W ， Teng S H and Zhang D . 2019 . Feature extraction methods for palmprint recognition： a survey and evaluation . IEEE Transactions on Systems， Man， and Cybernetics： Systems ， 49 （ 2 ）： 346 - 363 ［ DOI： 10.1109/TSMC.2018.2795609 http://dx.doi.org/10.1109/TSMC.2018.2795609 ］
Kang W X ， Liu Y ， Wu Q X and Yue X S . 2014 . Contact-free palm-vein recognition based on local invariant features . PLoS One ， 9 （ 5 ）： #e 97548 ［ DOI： 10.1371/journal.pone.0097548 http://dx.doi.org/10.1371/journal.pone.0097548 ］
Lee Y P . 2015 . Palm vein recognition based on a modified （2D） 2 LDA . Signal， Image and Video Processing ， 9 （ 1 ）： 229 - 242 ［ DO I： 10.1007/s11760-013-0425-6 http://dx.doi.org/10.1007/s11760-013-0425-6 ］
Lin S ， Wu W and Yuan W Q . 2015 . Investigation on palm vein biometrics based on the texture neighbor pattern . Chinese Journal of Scientific Instrument ， 36 （ 10 ）： 2330 - 2338
林森 ， 吴微 ， 苑玮琦 . 2015 . 采用纹理近邻模式的掌静脉生物特征识别研究 . 仪器仪表学报 ， 36 （ 10 ）： 2330 - 2338 ［ DOI： 10.19650/j.cnki.cjsi.2015.10.022 http://dx.doi.org/10.19650/j.cnki.cjsi.2015.10.022 ］
Ma R and Zhou L . 2020 . Unsupervised segmenting texture images based on Gabor filters and extended LTP operator . Journal of Image and Graphics ， 25 （ 3 ）： 442 - 455
马瑞 ， 周力 . 2020 . 结合Gabor滤波器和扩展LTP算子的无监督纹理图像分割 . 中国图象图形学报 ， 25 （ 3 ）： 442 - 455 ［ DOI： 10.11834/jig.190275 http://dx.doi.org/10.11834/jig.190275 ］
Minaee S and Wang Y . 2017 . Palmprint recognition using deep scattering network // 2017 IEEE International Symposium on Circuits and Systems （ISCAS） . Baltimore， USA ： IEEE： 1 - 4 ［ DOI： 10.1109/ISCAS.2017.8050421 http://dx.doi.org/10.1109/ISCAS.2017.8050421 ］
Mullick S S ， Datta S and Das S . 2018 . Adaptive learning-based k-nearest neighbor classifiers with resilience to class imbalance . IEEE Transactions on Neural Networks and Learning Systems ， 29 （ 11 ）： 5713 - 5725 ［ DOI： 10.1109/TNNLS.2018.2812279 http://dx.doi.org/10.1109/TNNLS.2018.2812279 ］
Najmabadi M and Moallem P . 2022 . Person-independent facial expression recognition based on local directional compact pattern . Optik ， 265 ： # 169549 ［ DOI： 10.1016/J.IJLEO.2022.169549 http://dx.doi.org/10.1016/J.IJLEO.2022.169549 ］
Rizki F ， Wirayuda T A B and Ramadhani K N . 2016 . Identity recognition based on palm vein feature using two-dimensional linear discriminant analysis // Proceedings of the 1st International Conference on Information Technology， Information Systems and Electrical Engineering （ICITISEE） . Yogyakarta， Indonesia ： IEEE： 21 - 25 ［ DOI： 10.1109/ICITISEE.2016.7803041 http://dx.doi.org/10.1109/ICITISEE.2016.7803041 ］
Wan H P ， Chen L ， Song H and Yang J . 2017 . Dorsal hand vein recognition based on convolutional neural networks // Proceedings of 2017 IEEE International Conference on Bioinformatics and Biomedicine （BIBM） . Kansas City， USA ： IEEE： 1215 - 1221 ［ DOI： 10.1109/BIBM.2017.8217830 http://dx.doi.org/10.1109/BIBM.2017.8217830 ］
Wang H B ， Li M W ， Zhou J and Tao L . 2018 . Double Gabor orientation weber local descriptor for palmprint recognition . Journal of Electronics and Information Technology ， 40 （ 4 ）： 936 - 943
王华彬 ， 李梦雯 ， 周健 ， 陶亮 . 2018 . 基于双Gabor方向韦伯局部描述子的掌纹识别 . 电子与信息学报 ， 40 （ 4 ）： 936 - 943 ［ DOI： 10.11999/JEIT170657 http://dx.doi.org/10.11999/JEIT170657 ］
Wang H L ， Li S J ， Jia W and Liu X P . 2019 . Performance evaluation of convolutional neural network in palmprint recognition . Journal of Image and Graphics ， 24 （ 8 ）： 1231 - 1248
王海纶 ， 李书杰 ， 贾伟 ， 刘晓平 . 2019 . 卷积神经网络在掌纹识别中的性能评估 . 中国图象图形学报 ， 24 （ 8 ）： 1231 - 1248 ［ DOI： 10.11834/jig.180605 http://dx.doi.org/10.11834/jig.180605 ］
Wang J G ， Yau W Y ， Suwandy A and Sung E . 2008 . Person recognition by fusing palmprint and palm vein images based on “Laplacianpalm” representation . Pattern Recognition ， 41 （ 5 ）： 1514 - 1527 ［ DOI： 10.1016/j.patcog.2007.10.021 http://dx.doi.org/10.1016/j.patcog.2007.10.021 ］
Wang N . 2011 . Research on Palm Vein Extraction and Recognition Method . Shenyang ： Shenyang University of Technology
王楠 . 2011 . 手掌静脉特征提取与识别方法研究 . 沈阳 ： 沈阳工业大学
Wu K S ， Lee J C ， Lo T M ， Chang K C and Chang C P . 2013 . A secure palm vein recognition system . Journal of Systems and Software ， 86 （ 11 ）： 2870 - 2876 ［ DOI： 10.1016/j.jss.2013.06.065 http://dx.doi.org/10.1016/j.jss.2013.06.065 ］
Wu W and Yuan W Q . 2013 . A survey of palm-vein image recognition . Journal of Image and Graphics ， 18 （ 10 ）： 1215 - 1224
吴微 ， 苑玮琦 . 2013 . 手掌静脉图像识别技术综述 . 中国图象图形学报 ， 18 （ 10 ）： 1215 - 1224 ［ DOI： 10.11843/jig.20131001 http://dx.doi.org/10.11843/jig.20131001 ］
Wulandari M ， Basari and Gunawan D . 2019 . On the performance of pretrained CNN aimed at palm vein recognition application // Proceedings of the 11th International Conference on Information Technology and Electrical Engineering （ICITEE） . Pattaya， Thailand ： IEEE： 1 - 6 ［ DOI： 10.1109/ICITEED.2019.8929938 http://dx.doi.org/10.1109/ICITEED.2019.8929938 ］
Xue Y ， Chen C ， Wang C S ， Li L G and Mansour R F . 2021 . Face image compression and reconstruction based on improved PCA . Intelligent Automation and Soft Computing ， 30 （ 3 ）： 973 - 982 ［ DOI： 10.32604/IASC.2021.017607 http://dx.doi.org/10.32604/IASC.2021.017607 ］
Yuan W Q ， Wu W ， Lin S ， Song H and Zhang H T . 2013 . Non-contact palm vein biometric recognition based on block and partial least squares . Chinese Journal of Scientific Instrument ， 34 （ 7 ）： 1470 - 1478
苑玮琦 ， 吴微 ， 林森 ， 宋辉 ， 张洪涛 . 2013 . 基于分块和偏最小二乘的非接触式手掌静脉生物特征识别 . 仪器仪表学报 ， 34 （ 7 ）： 1470 - 1478 ［ DOI： 10.19650/j.cnki.cjsi.2013.07.005 http://dx.doi.org/10.19650/j.cnki.cjsi.2013.07.005 ］
Zeng J Y ， Chen Y ， Qin C B ， Gan J Y ， Zhai Y K and Feng W L . 2019 . Finger vein image quality assessment based on cascaded fine-tuning convolutional neural network . Journal of Image and Graphics ， 24 （ 6 ）： 902 - 913
曾军英 ， 谌瑶 ， 秦传波 ， 甘俊英 ， 翟懿奎 ， 冯武林 . 2019 . 级联优化CNN的手指静脉图像质量评估 . 中国图象图形学报 ， 24 （ 6 ）： 902 - 913 ［ DOI： 10.11834/jig.180511 http://dx.doi.org/10.11834/jig.180511 ］
Zhang D ， Guo Z H ， Lu G M ， Zhang L and Zuo W M . 2010 . An online system of multispectral palmprint verification . IEEE Transactions on Instrumentation and Measurement ， 59 （ 2 ）： 480 - 490 ［ DOI： 10.1109/TIM.2009.2028772 http://dx.doi.org/10.1109/TIM.2009.2028772 ］
Zhang L ， Li L D ， Yang A Q ， Shen Y and Yang M . 2017 . Towards contactless palmprint recognition： a novel device， a new benchmark， and a collaborative representation based identification approach . Pattern Recognition ， 69 ： 199 - 212 ［ DOI： 10.1016/j.patcog.2017.04.016 http://dx.doi.org/10.1016/j.patcog.2017.04.016 ］
Zhang Z L ， Xie H and Zhang X F . 2016 . An improved algorithm for hand feature points localization based on disk method . Applied Science and Technology ， 43 （ 6 ）： 62 - 66
张真林 ， 谢红 ， 张秀峰 . 2016 . 圆盘法的手形特征点定位改进算法 . 应用科技 ， 43 （ 6 ）： 62 - 66 ［ DOI： 10.11991/yykj.201508018 http://dx.doi.org/10.11991/yykj.201508018 ］
相关文章
相关作者
相关机构
京公网安备11010802024621
