Name
Abstract | ||
|---|---|---|
A novel method for liveness detection of dorsal hand vein (DHV) based on AR model is proposed. Firstly, existing real DHV images are used to constitute a projection space based on modified principal component analysis (PCA). Unlike the previous works using the method of PCA, zero eigenvalues with their eigenvectors are used to constitute the projection space in this work. Secondly, test samples, including both real and fake DHV images, are projected to the projection space to produce one-dimensional vectors to extract their noise information. Then, autoregressive (AR) model is established for each test sample by estimating the power spectrum of the vector to detect the liveness of DHV. The proposed method is tested on a database of 510 real DHV images and 300 fake DHV images of 3 different types. The experimental results show that the proposed method performs well with an average recognition rate of 99%. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ComComAp.2014.7017197 | ComComAP |
Keywords | DocType | Citations |
autoregressive processes,eigenvalues and eigenfunctions,image recognition,principal component analysis,1d vectors,ar model,dhv images,pca,autoregressive model,average recognition rate,database,dorsal hand vein,eigenvalues,eigenvectors,liveness detection,noise information,projection space,databases,noise,vectors | Conference | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| yiding wang | 1 | 138 | 19.17 |
| Qi Qi | 2 | 0 | 0.34 |
| Kefeng Li | 3 | 9 | 2.97 |