Author Affiliations
School of Electronic and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, Chinashow less
Fig. 1. Kirsch operator in eight directions
Fig. 2. Sobel operator in eight directions
Fig. 3. Sobel operator directional setting
Fig. 4. Edge response values
Fig. 5. SLDP encoding example
Fig. 6. LDP and SLDP anti-noise tests. (a) Uninterrupted image; (b) image with noise
Fig. 7. BSLDP histogram feature extraction
Fig. 8. Overall block diagram of the system
Fig. 9. Actual acquisition device
Fig. 10. Image ROI example. (a) CASIA-M image database; (b) self-built non-contact image database
Fig. 11. Result curves. (a) Matching result curve; (b) ROC curve
Fig. 12. Result curves. (a) Matching result curve; (b) ROC curve
Database | Capturemethod | Lightsource | Testsample |
---|
CASIA-M | Non-contact | White light /850 nm nearinfrared light | 6×100 | Self-builtnon-contact | Non-contact | White light /850 nm nearinfrared light | 5×100 |
|
Table 1. Basic situation of the experimental samples
Matchingtype | CASIA-Mdatabase | Self-built non-contact database |
---|
Intra-class | 1500 | 1000 | Inter-class | 178200 | 123750 |
|
Table 2. Number of matching
Imageblock | CASIA-M /% | Self-built non-contact database /% |
---|
1×1 | 5.34 | 9.04 | 2×2 | 3.36 | 6.37 | 4×4 | 2.08 | 2.82 | 8×8 | 0.63 | 1.21 | 16×16 | 1.32 | 1.78 | 32×32 | 2.93 | 3.76 |
|
Table 3. EER with different blocks
Algorithm | EER of CASIA-M database /% | EER of self-built non-contact database /% |
---|
Palmprint | Palm vein | Palmprint | Palm vein |
---|
2DGabor | 7.17 | 7.93 | 5.17 | 1.97 | SURF | 4.77 | 10.6 | 4.89 | 3.10 | LBP | 6.85 | 8.20 | 7.59 | 8.11 | LDP | 4.98 | 7.01 | 6.22 | 7.43 | BSLDP | 0.82 | 1.03 | 2.16 | 2.53 | MMNBP | 1.34 (fusion) | 3.09 (fusion) | Ref. [10] | 0.75 (fusion) | 1.52 (fusion) | Ref. [20] | 1.07 (fusion) | 1.56 (fusion) | Proposed algorithm | 0.63(fusion) | 1.21 (fusion) |
|
Table 4. Comparison of EER between the proposed algorithm and other algorithms
Algorithm | Recognition time of CASIA-M database /s | Recognition time of self-built non-contact database /s |
---|
Palmprint | Palm vein | Palmprint | Palm vein |
---|
2DGabor | 0.0972 | 0.1631 | 0.1215 | 0.2594 | SURF | 0.1062 | 0.2457 | 0.2533 | 0.3630 | LBP | 0.0199 | 0.0434 | 0.0715 | 0.1037 | LDP | 0.0847 | 0.1081 | 0.1008 | 0.1236 | BSLDP | 0.0503 | 0.0610 | 0.0597 | 0.0812 | MMNBP | 0.1060 (fusion) | 0.1251 (fusion) | Ref. [10] | 0.1670 (fusion) | 0.1904 (fusion) | Ref. [20] | 0.1039 (fusion) | 0.1503 (fusion) | Proposed algorithm | 0.0765 (fusion) | 0.1024 (fusion) |
|
Table 5. Comparison of recognition time between the proposed algorithm and other algorithms