**3. Data analysis**

*Biometric Systems*

**12**

**Reference**

[6] [5]

• •

> [11]

[27]

• •

**Table 4.**

*Applications used with the advantages and disadvantages.*

Pattern matching

Minutiae-based matching

Uses the ridges and valley structures of input

Improves the goodness index and the

\_

verification accuracy

fingerprint images.

Pattern matching

Fingerprint verification

\_

system

Minutiae-based matching

\_

Correlation-based fingerprint

verification system

**Methods used**

**Reason of application**

To match tow fingerprint depending on gray level

fingerprint images.

**Advantages** Work well with bad quality fingerprint

\_

\_

image.

\_

\_

\_

**Disadvantages**

This section analyses the fingerprint recognition data resulting from the literature [1–27] survey in Section 2. In general, fingerprint recognition processes can be done using multiple procedures. First, decompose raw human fingerprint sample to create digit presentation of the same sample. On the next step, preprocessing is done for the raw input image by filtering and improving fingerprint image to produce suitable output image for feature extraction which extracts the unique features of the fingerprint from the digital representation sample. These extracted features are saved in the fingerprint database as features. Final step is to match the input fingerprint with fingerprint template stored in the database to find the similarities. The outcome of these procedures is deciding if the person is identified or not [8]. **Figure 2** describes the sequence of biometric or fingerprint system. The fingerprint procedures involve many different approaches and algorithms that are used to enhance and improve the low quality of fingerprint images. If the fingerprint image is on good quality, then there are no issues and will appear while matching [4]. **Table 1** presents the approaches that are used by different authors. **Figure 3** presents the most used approaches. Different matching approaches are used in 15 papers which can be considered as the commonly used approaches. Then minutiae extraction techniques are used in around 10 papers. Post processing and histogram equalization are used in 2 papers. There are some other approaches used only once in some of the papers.

When the matching process is completed. Correctness of a fingerprint identification system is calculated by applying some parameters. It is used to measure the performance of identification and verification. The performance measures used for identification depend mostly on the accuracy, testing time and image quality. **Figure 4** confirms that 38% of the work used the accuracy as the main identification measure and applied it alone or in addition to other measures. On the other

**Figure 2.** *Biometric or fingerprint system.*

**Figure 3.** *The most used fingerprint approaches in various papers.*

**Figure 4.** *The identification measures used in the work.*

hand, the most applied performance measures for verification are False Match Rate (FMR), False Non-Match Rate (FNMR), False Accept Rate (FAR) and False Rejection Rate (FRR). As shown in **Figure 5**, approximately 36% of the papers rely on (FAR) as a verification measure.

In the fingerprint recognition area, conducting test and experiments is important to approve and evaluate the quality and accuracy of the proposed work. Many different data bases have been used to test the performance of the proposed matching algorithms. These databases vary in their sizes, average number of templets and input fingerprints. **Figure 6** describes the databases types used in the study. As noticed from **Table 3**, FVC2000 and FVC2002 databases are used in some papers but most papers used their own databases. For example, authors in [24] used Biometric System Lab (University of Bologna – Italy). The used databases contain a several number of fingerprints that are used to produce fingerprint images. These images are used in matching step. **Figure 7** shows the discerption of the used databases characteristics by presenting the number of identities and the number of images.

**15**

**Figure 7.**

*Used database characteristics.*

**Figure 5.**

**Figure 6.**

*The used databases in the papers.*

*The verification measures used in the work.*

*Introductory Chapter: On Fingerprint Recognition DOI: http://dx.doi.org/10.5772/intechopen.95630*

*Introductory Chapter: On Fingerprint Recognition DOI: http://dx.doi.org/10.5772/intechopen.95630*

*Biometric Systems*

**Figure 3.**

**Figure 4.**

**14**

hand, the most applied performance measures for verification are False Match Rate (FMR), False Non-Match Rate (FNMR), False Accept Rate (FAR) and False Rejection Rate (FRR). As shown in **Figure 5**, approximately 36% of the papers rely

by presenting the number of identities and the number of images.

In the fingerprint recognition area, conducting test and experiments is important to approve and evaluate the quality and accuracy of the proposed work. Many different data bases have been used to test the performance of the proposed matching algorithms. These databases vary in their sizes, average number of templets and input fingerprints. **Figure 6** describes the databases types used in the study. As noticed from **Table 3**, FVC2000 and FVC2002 databases are used in some papers but most papers used their own databases. For example, authors in [24] used Biometric System Lab (University of Bologna – Italy). The used databases contain a several number of fingerprints that are used to produce fingerprint images. These images are used in matching step. **Figure 7** shows the discerption of the used databases characteristics

on (FAR) as a verification measure.

*The identification measures used in the work.*

*The most used fingerprint approaches in various papers.*

**Figure 5.** *The verification measures used in the work.*

**Figure 6.** *The used databases in the papers.*

**Figure 7.** *Used database characteristics.*

#### **Figure 8.**

*Accuracy and performance from the used papers.*

At last, the evaluation of the performance or accuracy of the fingerprint verification system are appearing in 4 papers as presented in **Figure 8**. The figure shows the highest accuracy with 95% and the lowest accuracy with 45%.

## **4. Conclusion**

Biometrics means the automatic identification of a person based on his behavioral and/or physiological unique characteristics. Fingerprint biometrics is an efficient, safe, cost-effective, easy to use the technique for identity verification. This study provides detailed information related to fingerprint recognition techniques. Several author's works, related to fingerprint recognition technology, are discussed, compared and analyzed. A detailed analysis of various studies is made. As a future work, there is a scope to improve the problems related to fingerprint recognition, specially, the issues related to the capturing row fingerprint by the sensors. One of the innovations is the touchless fingerprint sensor, which will be sufficient for current (COVID-19) situations. It will decree the need to touch the devices. This technique is needed to show its reliability and efficacy as an alternative to regular sensors. Relying on a fingerprint recognition in a different government domains is also recommended. Implementing fingerprint recognition technology is not only useful for Government, but other organizations and communities can also think and may benefit by applying fingerprint recognition techniques to identify. For example, in the health sector, it is quite important to use fingerprint recognition to identify the person injured in an accident.

**17**

**Author details**

Muhammad Sarfraz

hawra.alhussain@grad.ku.edu.kw

provided the original work is properly cited.

Department of Information Science, College of Life Sciences, Kuwait University,

© 2021 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium,

Sabah AlSalem University City, Shadadiya, Kuwait

\*Address all correspondence to: prof.m.sarfraz@gmail.com;

*Introductory Chapter: On Fingerprint Recognition DOI: http://dx.doi.org/10.5772/intechopen.95630*

*Introductory Chapter: On Fingerprint Recognition DOI: http://dx.doi.org/10.5772/intechopen.95630*

*Biometric Systems*

**4. Conclusion**

*Accuracy and performance from the used papers.*

**Figure 8.**

At last, the evaluation of the performance or accuracy of the fingerprint verification system are appearing in 4 papers as presented in **Figure 8**. The figure shows the

Biometrics means the automatic identification of a person based on his behavioral and/or physiological unique characteristics. Fingerprint biometrics is an efficient, safe, cost-effective, easy to use the technique for identity verification. This study provides detailed information related to fingerprint recognition techniques. Several author's works, related to fingerprint recognition technology, are discussed, compared and analyzed. A detailed analysis of various studies is made. As a future work, there is a scope to improve the problems related to fingerprint recognition, specially, the issues related to the capturing row fingerprint by the sensors. One of the innovations is the touchless fingerprint sensor, which will be sufficient for current (COVID-19) situations. It will decree the need to touch the devices. This technique is needed to show its reliability and efficacy as an alternative to regular sensors. Relying on a fingerprint recognition in a different government domains is also recommended. Implementing fingerprint recognition technology is not only useful for Government, but other organizations and communities can also think and may benefit by applying fingerprint recognition techniques to identify. For example, in the health sector, it is quite important to use fingerprint recognition to

highest accuracy with 95% and the lowest accuracy with 45%.

identify the person injured in an accident.

**16**
