**2.3. Biometric fusion**

Biometric data may change over time or affected by environmental condition, so by fusing more than one trait or same trait from more than one source, we overcome the unimodal limitation and try to reduce one or more of the rejection and acceptance error rate based on the system requirements [17] as shown in **Figure 4**. Moreover, there is no one best biometrics since different applications require different policies such as distance learning, border control, and national identity card that require low false accept rate and failure to enroll. However, fusion is key to increase the recognition rate and can be taken at different stages (sensor, decision, feature extraction, classification stage).

**Figure 4.** Performance evaluation.

Sanderson and Paliwal et al. [18] divide the fusion into two categories: before classification called pre-matching and after classification called post-matching as shown in **Figure 5**:

	- **1.** Sensor level: integrating the raw data is difficult because it has a lot of unimportant features not only the region of interest and data collected from the sensors can be suffered from noisy as nonuniform illumination. Sensor-level fusion refers to raw data obtained using multiple sensors or multiple snapshots of a biometric using a single sensor. Face images collected from multiple sources with different resolutions may not be possible to integrate together.
	- **2.** Feature level: in feature-level fusion, we get a lot of information by producing one feature set from fusing different features that are extracted from the captured images. So feature sets need to be tuned, normalized, transformed, and reduced. In practice, it is difficult to achieve feature-level fusion because concatenating different features may lead to dimensionality problem.
	- **1.** At score stage [23]: scores combined to generate one score value to and used for making decision according to the threshold value. Threshold making the system more reliable than using true and false since there is range can be tuned to increase or decrease the false acceptance rate and false rejected rate. However, a lower threshold decreases the rate of falsely rejected rate but also increases the rate of falsely accepted rate.

**Figure 5.** Fusion levels.

**Biometric system can work in two modes:**

sion, feature extraction, classification stage).

stored in the dataset.

42 Machine Learning and Biometrics

**2.3. Biometric fusion**

**Figure 4.** Performance evaluation.

Identification either in identification mode or verification mode. Identification mode works as one to many by comparing the individual with all the templates stored in the dataset, while a verification mode works as one to one by comparing the individual with his own template

Biometric data may change over time or affected by environmental condition, so by fusing more than one trait or same trait from more than one source, we overcome the unimodal limitation and try to reduce one or more of the rejection and acceptance error rate based on the system requirements [17] as shown in **Figure 4**. Moreover, there is no one best biometrics since different applications require different policies such as distance learning, border control, and national identity card that require low false accept rate and failure to enroll. However, fusion is key to increase the recognition rate and can be taken at different stages (sensor, deci**2.** At rank stage [24]: the score values are arranged in descending order showing the possibility of the decision that at top list most preferred classes are placed and at down list least preferred classes.

• Environmental factors as high temperature, steam, and rain humidity lead to low accuracy. The features change over time as age and performance. The age, gender, ethnic, and face

A Survey on Soft Biometrics for Human Identification http://dx.doi.org/10.5772/intechopen.76021 45

• User willing and wishes: since users don't need to deal with the system intentionally, the

• The plastic surgery patients and people who don't have a hand cannot use a fingerprint.

All the measurement rates are affected by the above factors, so any biometric system needs to calculate the error factors and tune and normalize them according to the system require-

Alphonse Bertillon, who firstly introduced the idea of personal identification system based on biometric, morphological, and anthropometric using color of the eyes, hair, and skin in 1896. Face recognition is lower in uniqueness and more acceptable than iris but still is user-friendly, and people are willing to use it than other techniques [27]. The soft biometric is divided into

• Global traits are used for dataset indexing that remain fixed for the whole life as ethnicity

• Head features, this is where the research is heading now because of the rich feature in this

Soft biometric traits also can be classified according to permanence and distinctiveness as shown in **Table 1**. The permanence of a trait shows the strength of the trait over the period of time as gender and ethnicity don't change over time. Distinctiveness refers to the ability of a

• Body features are used to describe an individual height and weight as tall or fat.

**Soft biometric traits Face Permanence Distinctiveness** Facial measurements Face High Medium Gender Face High Low Skin color Face Medium Low Eye color Face Medium Medium Tattoo Face High High Age Face Low Medium Mustache Face Low Low

body part as facial measurements and skin and hair color.

pose.

ments and nature.

three groups as follows [28]:

trait to differentiate between individuals.

**Table 1.** Facial soft biometric traits.

and sex.

system get affected and accuracy decrease.

**3. Literature review and related work**

