**4. Feature reduction and data fusion**

The multi-biometric system has been tested using certain parts of the following databases: PolyU palmprint [24], IIITD periocular database [25], and Bosphorus

### *Multimodal Biometrics for Person Authentication DOI: http://dx.doi.org/10.5772/intechopen.85003*

hand vein database [35]. We choose 20 subjects with 10 images per subject at random. From 10 images, 5 images are used for training and 5 for the testing.

The combination of feature vectors at this level is difficult to achieve in practice due to the combination of certain fundamentally different feature vectors that can result in a resulting vector of features with very large dimensionality. In a merger at the level of feature vectors, each individual modality process generates a feature vector. The fusion process combines these feature vectors into one vector.

For dorsal vein images and for palm print images, we perform the same image processing operations that the feature vectors have the same sizes. As a result of convolution operation of multiscale and multi-orientation Gabor filters with the input image, we get the Gabor response images. The feature vector has a very large size of *(M x N x k x l)* where *MxN* is the image size, *k* is the number of scales, and *l* is the number of orientations. In our case, for both dorsal vein images and palm print images, we get a feature vector containing (150 � 150 � 3 � 6) = 405,000 items. The images subjected to the Gabor filtration are rescaled with a scale factor of 0.1, which allows obtaining a vector of features with a size of 1 � 4050 elements.

For periocular images, the feature vector has a size of 36 � 59 = 2124.

Next we reduce dimensionality of these vectors used in PCA method (**Figure 14** and **Table 4**) [5]. Separated features are normalized using zero mean and unit variance as

**Figure 14.** *Steps to image processing using PCA.*

*H k*ð Þ¼ ∑

*The LBPP,R histogram (a), histograms of the* n *blocks (b), and the LBPu*<sup>2</sup>

*The original image (a) and image as a result of the LBP operator (b).*

*Security and Privacy From a Legal, Ethical, and Technical Perspective*

of the histogram).

**Figure 12.**

**Figure 13.**

*of LBP<sup>u</sup>*<sup>2</sup>

**188**

standard *LBPP,R* operator and an *LBP<sup>u</sup>*<sup>2</sup>

**4. Feature reduction and data fusion**

catenate into feature vector [34].

*M i*¼1 ∑ *N j*¼1

f x*;* <sup>y</sup> <sup>¼</sup> <sup>1</sup>*,* <sup>x</sup> <sup>¼</sup> <sup>y</sup>

where *k* is one *LBP* pattern and *K* is the maximal *LBP* pattern value (number bin

Using the *LBP* operator, we obtain 2*<sup>P</sup>* different output values corresponding to

*P,R* operator. Typically image is divided into *n* blocks and histograms of each block are con-

The multi-biometric system has been tested using certain parts of the following databases: PolyU palmprint [24], IIITD periocular database [25], and Bosphorus

2*<sup>P</sup>* different binary patterns created by *P* of neighboring pixels. Certain binary patterns contain more information than others, so we can only consider this subset of *LBP* values. Patterns of this subset are called uniform patterns. So we have a

In the case *LBPP,R* operator, the histogram contains 256 bins. In the case

*P,R* operator, the histogram contains 59 bins (**Figures 12** and **13**).

0*,* otherwise

*f LBP* ð Þ *P,R*ð Þ *i; j ; k ; k*∈½ � 0*;K* (5)

*P,R histogram (c).*


for *v* ¼ ð Þ *v*1*; v*2*;* ⋯*; vk*

**Table 4.** *PCA algorithm.*

### *Security and Privacy From a Legal, Ethical, and Technical Perspective*


**Table 5.**

*Recognition rates [%] for different modality.*

$$
\overline{f}\_i = \frac{f\_i - \mu\_i}{\sigma\_i} \tag{6}
$$

**References**

[1] Ross AA, Nandakumar K, Jain AK. Handbook of Multibiometrics. Boston,

*Multimodal Biometrics for Person Authentication DOI: http://dx.doi.org/10.5772/intechopen.85003*

at Biometric Consortium Conference;

[10] Froba B, Rothe C, Kublbeck C. Evaluation of sensor calibration in a biometric person recognition

framework based on sensor fusion. In: Proceedings of 4th IEEE International Conference on Automatic Face & Gesture Recognition; 2000. pp. 512-517

[11] Meraoumia A, Chitroub S, Bouridane A. Multimodal biometric person recognition system based on fingerprint & finger-knuckleprint using

correlation filter classifier. In:

Proceedings of the IEEE International Conference on Communications; 2012.

[12] Bhaskar B. Veluchamy S. Hand based multibiometric authentication using local feature extraction. In: Proceedings of the International Conference on Recent Trends in Information Technology; 2014. pp. 1-5

[13] Bokade GU, Sapkal AM. Feature level fusion of palm and face for secure recognition. International Journal of Electrical and Computer Engineering.

[14] Hossain E, Chetty G. Multimodal face-gait fusion for biometric person authentication. In: Proceedings of the IFIP 9th International Conference on Embedded Ubiquitous Computing;

[15] Ding Y, Zhuang D, Wang K. A study of hand vein recognition method. In: Proceedings of the IEEE International Conference on Mechatronics & Automation; 2005. pp. 2106-2110

[16] Miao D, Sun Z, Huang Y. Fusion of multibiometrics based on a new robust linear programming. In: Proceedings of the 22nd International Conference on Pattern Recognition; 2014. pp. 291-296

2006. pp. 1-6

pp. 820-824

2012;**4**(2):157

2011. pp. 332-337

[2] Travieso CM, del Pozo-Baños M, Alonso JB. Fused intra-bimodal face verification approach based on scaleinvariant feature transform and a vocabulary tree. Pattern Recognition

[3] Travieso CM, Zhang J, Miller P, Alonso JB, Ferrer MA. Bimodal

[4] Ross A. An introduction to

[5] Long TB, Thai LH, Hanh T. Multimodal biometric person

2012. pp. 613-624

2010;**5**(1):52-61

2003;**24**(13):2115-2125

**191**

biometric verification based on face and lips. Neurocomputing;**74**(14–15):

multibiometrics. In: Proceedings of the 15th European Signal Processing Conference; 2007. pp. 20-24

authentication using fingerprint, face features. In: Anthony P, Ishizuka M, Lukose D, editors. Trends in Artificial Intelligence (LNCS 7458). Springer;

[6] Choi H, Choi K, Kim J. Mosaicing touchless and mirror-reflected

fingerprint images. IEEE Transactions on Information Forensics and Security.

[7] Ghouti L, Bahjat AA. Iris fusion for multibiometric systems. In: Proceedings of the IEEE International Symposium on Signal Processing and Information Technology; 2009. pp. 248-253

[8] Ross A, Jain A. Information fusion in biometrics. Pattern Recognition Letters.

[9] Chen Y, Parziale G, Diaz-Santana E, Jain AK. 3D touchless fingerprints: Compatibility with legacy rolled images. In: Proceedings of the Biometrics Symposium: Special Session on Research

MA, USA: Kluwer; 2006

Letters;**36**:254-260

2407-2410

where *μ<sup>i</sup>* and *σ<sup>i</sup>* are the mean value and standard deviation of the *i*-th feature, *fi* is the normalized *i*-th feature vector.

**Table 5** shows the recognition performance depending on the number of selected eigenvectors.

### **5. Conclusion**

In this chapter, Gabor's functions and LBP features are proposed for recognition in a multi-biometric system that uses three modalities: dorsal vein, periocular, and palm print. Using PCA method dimensionality feature vectors from these modality are reduced. Feature vectors are normalized and fused using concatenation operation. Based on the results, we suggest that multi-biometric system using the fusion of dorsal vein, periocular, and palm print images can offer recognition rate which the unimodal biometric system cannot.
