**2. Literature survey**

Fingerprint recognition is the procedure of comparing known and unknown fingerprints to prove that the it is from the same person or not [8]. Today, many approaches, techniques, and systems are used to match fingerprints and solve related problems. This section is focused on analyzing and categorizing different author's work in the fingerprint recognition area. **Table 1** provides a summary of various papers in the current literature. First column determines the Reference of the papers by author names and year of publication. Second column gives the summary of the work in the corresponding paper, and the third column describes the implemented approaches used to solve fingerprint recognition issues. The author names and the year of publication will be used as an identifier for the rest of the tables in the chapter showing other details of the referred literature.


**3**

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

[21] Beneficent of minutiae-based fingerprint verification system by suggesting a route for the feature extraction step which depends on reexamining the gray-scale profile can increase the matching performance by 4%. Also, the proposed feature refinement step that allocates class labels for every 31qmintiae will improve the performance by 3%. Both steps will develop the whole fingerprint

verification system be 8%.

MATLAB environment.

[17] Design minutia extractor by using different

implemented in the work.

[24] Combining minutia and correlation-based

[2] Present Fingerprint Recognition using the Minutia

[1] A summary of several biometrics techniques as well

[3] Explaining some biometrics and dividing them to

[15] An alignment-based minutia-matching algorithm

and understudy biometrics.

workstation.

their pros and cons.

[18] Execution and assessment of Biometric Image

Software (NBIS) for fingerprint recognition developed by the National Institute of Standards and Technology (NIST). the NBIS is implemented in the

techniques. Some improvements in the thinning, false removal approach, and image segmentation is

approaches to evolve an automatic fingerprint recognition system. By using this hybrid, the performance of the minutiae algorithm is grown.

Score Matching method (FRMSM). It implements Block Filter for fingerprint thinning. Also, it compares with available algorithms.

as explaining the unimodal and multimodal with

currently in use biometrics, limited used biometrics,

has been developed to increase the speed and accuracy by ability determining the matches between input minutiae and Stord one without the need for detailed study. Michigan State University and the National Institute of Standards and Technology NIST 9 fingerprint databases have been used. The result shows that the full verification process takes 1.4 seconds a Sun ULTRA 1

**Reference Brief summary Approaches adopted**

Sequential approach

• Pre-processing • Minutiae Extraction • Post processing

• Segmentation using Morphological operations

• False minutiae removal

three termination • Matching in the unified x-y coordinate system

• Minutiae Extraction • Post-processing • Minutiae Matching

• Filtering • Feature Vector

• Thinning • Image binarizing • Noise removal

• Sensor module • Matching module • Decision-making module

• Feature extraction module

Alignment-based minutiaematching algorithm

Fusion scheme

• Thinning

methods • Minutia marking • Minutia unification by decompose-ng a branch into *Biometric Systems*

fingerprint recognition.

**2. Literature survey**

tions, and conclusion are presented in Section 4.

in terms of accuracy, effectiveness, speed, advantages, and challenges [5]. This chapter discusses, compares and analyses several authors work [1–27] regarding the

The remaining of the chapter is organized as follows. Section 2 is an overview of the literature survey with comparative research. Section 3 deals with a detailed analytical study of the literature review. At last, future directions, recommenda-

Fingerprint recognition is the procedure of comparing known and unknown fingerprints to prove that the it is from the same person or not [8]. Today, many approaches, techniques, and systems are used to match fingerprints and solve related problems. This section is focused on analyzing and categorizing different author's work in the fingerprint recognition area. **Table 1** provides a summary of various papers in the current literature. First column determines the Reference of the papers by author names and year of publication. Second column gives the summary of the work in the corresponding paper, and the third column describes the implemented approaches used to solve fingerprint recognition issues. The author names and the year of publication will be used as an identifier for the rest of the

tables in the chapter showing other details of the referred literature.

used for certification and recognition purpose with submitting their advantages and disadvantages.

recognition systems and patterns depending on the minute-based technique. Focused on Pattern recognition, wavelet, and wave atom mechanisms. Complications related to the wave atom method are

fingerprint matching techniques particularly local minutiae-based matching algorithms. It provides an experiment about fingerprint identification and authentication using the minutiae-based matching

extraction technique and covering all related systems

method with analyzing the outcomes.

[23] Discuses fingerprint authentication using minutiae

[8] Explains different biometrics structures that are

[4] A general explanation of various types of fingerprint

studied.

[20] Explains the differences between various

and processes.

**Reference Brief summary Approaches adopted**

• Knowledge-based approach • Token based approach • Biometric based approach

• Histogram Equalization • Band pass Filtering • Gabor Filtering

• Binarization and Thinning • 2D Fourier Transform • Wavelet based Transformation • Wave atom Transform and MCS optimization algorithm

• topology of local structure • type of consolidation • usage of additional features • minutiae peculiarities • parameter learning.

• Histogram Equalization • Fast Fourier Transformation

• Minutiae Extraction • False Minutiae Removal

• Load image

• Binarization • Region of Interest • Thinning

**2**



**5**

**Table 1.**

*Overview of the literature.*

**Table 2** shows the accuracy and performance in percentage. It also mentions the identification and verification measures. Identification and verification are matching techniques for fingerprint recognition. In the verification, the person enrolls his fingerprint to the system and the templet stored it in the database. Every time the person accesses the system, he has entered his fingerprint to verify himself. It's a one to one relationship where the input fingerprint is compared with the stored one. On the other hand, identification is one to many relationships because the human fingerprint is matched with the fingerprints database to determine who is that person [8].

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

system.

systems.

[13] Novel enhancement algorithm that split the input

[14] Submit a fingerprint recognition algorithm

performance using this approach.

[5] A brief summary of fingerprint matching techniques, systems, and performance evaluation.

> recognition. As biometric pattern, it highlights a detailed analysis on the fingerprint

conceptualization. It uses various tools to find the match percentage in the verification process.

algorithm, which can adaptively improve the clarity of ridge and valley structures of input fingerprint images based on the estimated local ridge orientation

[11] It provides important aspects of fingerprint

[27] This presents a fast fingerprint enhancement

and frequency.

[6] The correlation-based fingerprint verification

fingerprint image to set of filtered images which will help in producing orientation field and quality mask. The evaluation process of the algorithm is done on an online fingerprint verification system using the MSU fingerprint database that consists of 600 fingerprint images and the test demonstrates that the enhancement algorithm improves the performance of the online fingerprint verification

depending on phase-based image matching. Which uses the phase components in 2D (two-dimensional) discrete Fourier transforms of fingerprint images to reach strong fingerprint recognition with a low-quality fingerprint. The test used a group of fingerprint images captured from fingertips with a bad case. The results show an effective recognition

system uses the richer gray-scale information of the fingerprints. In the beginning, the system chooses appropriate templates in the primary fingerprint, employs template matching to locate them in the secondary print, and match the template positions of both fingerprints. The test describes the performance of correlation-based fingerprint against other

**Reference Brief summary Approaches adopted**

• Gabor filters

algorithm

transforms

positions

decisions

• Voting algorithm • Orientation estimation

• Ridge extraction algorithm

2D (two-dimensional) Fourier

• Classification of template

• Elementary decisions • Combining elementary

• Image capturing module • Feature extraction module • Pattern matching module

• Negative Laplace filter • Non-stationary analysis of the short time Fourier

• An algorithm to find the match percentage in the verification

• Goodness index of the extracted

• Accuracy of an online fingerprint verification system.

transform

process.

minutiae

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

*Biometric Systems*

**Reference Brief summary Approaches adopted**

• Image acquisition • Preprocessing • Minutiae detection • Minutiae reduction • Fingerprint matching

• Image acquisition • Preprocess-ng • Segmental-on • Minutia detection • Biometric matching

Novel topology-based representation technique

• Region estimation

(Line- DFT)

algorithm

• Orientation filed estimation • Fingerprint enhancement • Coarse density map extraction • Weighted polynomial approximation

• Column Principal Component Analysis (Column-PCA) • Line Discrete Fourier Transform

Core-based structure matching

Topology-matching algorithm

hybrid matching approach (minutiae-based representation

• Single pass thinning algorithm

with a texture-based representation)

• Contextual filter

• Image preprocess • Gabor filtering

gray level watershed process to find out the ridges present on a specific fingerprint image. The result display that this system is accurate and fast when

detail and explaining deferent types of algorithms like negative Laplace filter and the non-stationary analysis, and a flexible algorithm with calculating the

matching based on local structures to elicit neighboring minutiae features effectively. The presented algorithm is tested on FVC2002 and the results show the reliability of the system.

based matching where the density data can be used in the matching process to reduce extra storing cost. The outcomes approved that combining both

reduction ratio of 94% by applying tow reduction algorithms the Column Principal Component Analysis and the Line Discrete Fourier Transform feature reductions. Also, a fast minutiae-based matching algorithm can be accomplished throw spectral minutiae fingerprint recognition system which shows matching speed with 125000 comparisons per second on a PC with Intel Pentium

[22] Applying fingerprint identification by employing a

matching 7 images in the database.

[26] Discussing fingerprint recognition biometric in

matching test results.

[10] Developing a novel algorithm for fingerprint

[9] Mixing the density map matching with minutiae-

[12] An adequate wat to press the template size with a

approaches will improve performance.

D processor 2.80 GHz and 1 GB of RAM.

detection algorithm to examine the core point and determine local frame for minutiae close to it. Then tow fingerprint corresponding points will be earned and used to match the global class then make the

fingerprints using minutiae inputs and texture inputs together. The matching performance improved when testing 2560 images by collecting both texture-based

fingerprint recognition that provides good results for low-quality fingerprint images. Matching fingerprint images based on ridgeline features extracted by using contextual filtering and two pass thinning. Histogram approach is used to match the fingerprint. The experiments show how the performance

[25] Novel core point detection method that uses the

[7] New topology-based algorithms to match fingerprint and address the local matching, tolerance to deformation, and global matching. The experiment outcomes approve that time and performance is

improved using the algorithm.

[16] Provide a hybrid matching algorithm that matches

and minutiae-based matching scores.

[19] Suggesting ridge feature-based approach for

developed using this approach.

final diction.

**4**


#### **Table 1.**

*Overview of the literature.*

**Table 2** shows the accuracy and performance in percentage. It also mentions the identification and verification measures. Identification and verification are matching techniques for fingerprint recognition. In the verification, the person enrolls his fingerprint to the system and the templet stored it in the database. Every time the person accesses the system, he has entered his fingerprint to verify himself. It's a one to one relationship where the input fingerprint is compared with the stored one. On the other hand, identification is one to many relationships because the human fingerprint is matched with the fingerprints database to determine who is that person [8].


**7**

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

**Reference Application Database No. of** 

[21] Fingerprint IBM

[24] Fingerprint Biometric

[1] • Fingerprint • Face • Voice • Infrared thermogram (facial, hand or hand vein)

> • Gait • Keystroke • Odor • Ear

• Retina • Iris • Palmprint • Signature • DNA

• Hand geometry

While the performance measures used for identification depend on the accuracy, recognition rate, rank K, etc., the performance measures for verification are False Match Rate (FMR), False Non-Match Rate (FNMR), False Accept Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (EER). The researchers in [4] describe the meaning of the authentication parameters. FAR happens when the system recognizes person erroneous. But when the system rejects entry to approve person that means the FRR is happening. FMR is the amount of fraud assessments with threshold value 'T' divided by the total quantity of fraud similarities. FNMR is the quantity with unaffected comparisons with threshold value 'T' divided by the total quantity of

open comparisons. Last one is EER, it describes the error rate of the system.

The experimental parts of the author's [1–27] are shown in **Table 3**. It explains the type of applications and kind of Databases used. Then it shows the number of

[8] \_ \_ \_ \_ \_ \_ [4] Fingerprint \_ \_ \_ \_ \_ [20] Fingerprint FVC 308 1228 \_ \_ [23] Fingerprint \_ \_ \_ \_ \_

[18] Fingerprint FVC 2000 60 480 \_ \_ [17] Fingerprint \_ \_ 2 \_ \_

[2] Fingerprint \_ \_ \_ \_ \_

21 7

HURSLEY database

System Lab (University of Bologna - ITALY) Ink and scanner

FVC2002 FRVT2002 NIST2000

**identities**

**Total No. of images**

168 56

269 900 500dpi \_

\_ \_ \_ \_

256 × 256 × 256dpi 240× 240× 256dpi

**Resolution Image** 

**format**

\_

**Table 2.** *Accuracy and performance.*

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

*Biometric Systems*

**Reference Accuracy** 

[21] 95% (LVQ-based

data)

classifier on training data) 87% (LVQ-based classifier on test

**(Performance)**

[8] \_ \_ \_ [4] \_ FAR, FRR, FMR, FNMR,

[23] \_ FMR \_

[24] \_ FAR \_ [2] \_ FMR, FNMR \_

[3] \_ \_ \_

[10] \_ EER \_

[26] \_ false acceptance (FA),

[14] \_ EER, ZeroFMR, FNMR,

[5] \_ EER, FAR, FRR \_ [11] \_ \_ \_ [27] \_ \_ \_

[20] \_ FMR, FNMR, EER,

ERR

ROC, FMR100, FMR1000, Zero FMR

[18] \_ FNMR, FMR Reliability and quality [17] \_ FRR, FAR Quality and accuracy

[1] \_ FMR, FNMR, FTC, FTE accuracy, speed, resource

false rejection (FR), recognition rate (RR)

[9] \_ FAR, FRR Matching time and computation cost [12] \_ FAR, EER, GAR Recognition accuracy, matching speed

More than 45% \_ Accuracy and testing time.

[15] \_ FAR, FRR Accuracy, speed

[25] \_ FAR, FRR Matching time [7] \_ FRR, FAR Matching accuracy

[16] \_ GRA, FAR Computing time [19] 98% EER, FAR, FRR Matching accuracy [13] \_ \_ Reject Rate

FMR

[6] \_ FRR, FAR,FNMR Testing time

**Performance measures used for verification**

**Performance measures used for** 

True positive rate (TPR), R100, ZeroR, Cumulative Match Curve (CMC), Accuracy, computational time, rank k

requirements, acceptability, and

and robustness to poor image quality

circumvention.

Accuracy

Matching time Computing time

Recognition Rate

Accuracy

**identification**

Accuracy

FAR, GAR Classification accuracy,

**6**

**Table 2.**

*Accuracy and performance.*

While the performance measures used for identification depend on the accuracy, recognition rate, rank K, etc., the performance measures for verification are False Match Rate (FMR), False Non-Match Rate (FNMR), False Accept Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (EER). The researchers in [4] describe the meaning of the authentication parameters. FAR happens when the system recognizes person erroneous. But when the system rejects entry to approve person that means the FRR is happening. FMR is the amount of fraud assessments with threshold value 'T' divided by the total quantity of fraud similarities. FNMR is the quantity with unaffected comparisons with threshold value 'T' divided by the total quantity of open comparisons. Last one is EER, it describes the error rate of the system.

The experimental parts of the author's [1–27] are shown in **Table 3**. It explains the type of applications and kind of Databases used. Then it shows the number of



**9**

**Reference**

[8] [4]

• •

Pattern Recognition

Approach

•

> [20]

•

Minutiae-based local

•

Comparing tow fingerprints to gain a result of

• •

Simplicity

Simple and distortion tolerance.

•

Expensive computation, slow and

depend on the skin situation.

matching or nonmatching.

matching

• techniques

•

> [23]

[21] [18] [17] [24]

hybrid Automatic Fingerprint

Recognition System (Hybrid

APRS)

Minutiae Extraction

Technique

Biometric Image Software

(NBIS)

minutiae-based fingerprint

•

Resolve the gray scale profile in the neighbor-

\_

\_

hood of potential minutiae.

•

Understand the gray level image properties.

Used for fingerprint recognition in MATLAB

\_

Reduce execution time.

\_

Time consuming, bad performance for

images.

environment.

Used to reduce distortion for fingerprint

matching.

Hybrid between minutiae and correlation-based

• • •

improve the ridge algorithm.

Improve minutia algorithm.

Improve each technique individually.

\_

techniques to represent and match fingerprint.

verification system

Minutiae based matching

Indexing algorithms

Correlation-based matching

•

Calculate the similarities between tow

fingerprint images by the correlation within

corresponding.

•

Used when it's important to enter fast to the

fingerprint templates for recognition.

Minutia extracted from fingerprint and saved

Widely used and familiar.

Affected with the wet or dry skin.

in the database then the matching happened

between the stored and input fingerprint.

Wavelet based Approaches

Minutiae based approach

\_

\_

• • • verification.

The use of patterns for authentication purpose

Used on fingerprint pattern to carry out the

To compare the fingerprint patterns.

**Methods used**

**Reason of application**

**Advantages**

\_

•

Great accuracy rate.

**Disadvantages**

\_

•

Image with noise or encrypted cannot

be used, slow approach and fails to

determine real humans.

•

Not required finger printing or post

processing, work in the least three levels

of texture split to make the system

excellent and its fast process.

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

**Table 3.** *Overview of the used data.*


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

*Biometric Systems*

[3] • Fingerprint • Face • Iris

**Reference Application Database No. of** 

• Hand geometry • Palmprint • Speaker/voice • Signature • Ear shape • Knuckle crease • Brain/EEG • Heart sound/ ECG

[15] Fingerprint MSU

[22] Fingerprint Scanner

[26] Fingerprint commercial

[9] Fingerprint THU database

[12] Fingerprint MCYT

[25] Fingerprint Live

[19] Fingerprint NRC

[7] Fingerprint fingerprint

fingerprint data base NIST 9 (card 70 1350 1350

NIST 9 (card

or inked impression

databases

FCV2002

FVC2002-DB2

fingerprint database

database at University of Bologna, Italy

FVC2000 database

[10] Fingerprint FVC2002 400 3200 \_ \_

[16] Fingerprint \_ 160 2560 \_ \_

[13] Fingerprint MSU 67 670 640\*480 \_ [14] Fingerprint \_ 30 330 256 × 384 \_ [6] Fingerprint FVC2000 110 880 \_ \_ [5] Fingerprint \_ \_ \_ \_ \_ [11] Fingerprint \_ \_ \_ \_ \_ [27] Fingerprint \_ \_ \_ \_ \_

827 100

145 40

1)

2)

**identities**

**Total No. of images**

\_ \_ \_ \_ \_

700 900 900

40 \_ 300 x 300

6616 800

1740 400

640 X 480 832 X 768 832 X 768

\_ 7 250 X 250 pixels TIF and

512 DPI

\_ 8000 300\*300 \_

21 1680 256 × 256 \_

\_ 300 200 × 200 \_

320X512 \_

\_ \_

**Resolution Image** 

**format**

\_

BMP

\_

**8**

**Table 3.**

*Overview of the used data.*


**11**

**Reference**

[12] [25]

• •

> [7]

[16] [19] [13] [14]

Phase-based image matching

\_

Online fingerprint verification

\_

system.

Ridge feature-based approach

Uses the ridges to match two fingers.

• • • images.

\_

• Slow.

•

Fail to devolve the clarity of ridges

structure for good quality fingerprint

templet.

Good results when using bad condition

\_

fingertips.

Powerful with low quality fingerprint

Increase matching accuracy.

Need little processing.

Minutiae- based matching

\_

\_

algorithms

Minutiae- based matching

For matching the fingerprints to find the similarities between them.

Good matching capability

• • •

High cost process.

Hard to nonlinear deformations of fingerprints

Not enough corresponding points in the

input images.

\_

The missing minutiae should be considered.

Core-based matching algorithms

Structure-based matching algorithms

\_\_

Spectral minutiae fingerprint recognition system

**Methods used**

**Reason of application**

Used to represent a minutia set as a fixed-length feature vector

**Advantages**

> •

• • •

More effective algorithm

• •

Highly depends on core point detection precision

Not suitable for online applications and require long time.

Low matching time.

Suitable for large scale fingerprint identification system.

High speed operations.

\_

**Disadvantages**

*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*

**10**

**Reference**

[2] [1]

• systems

• system

[3]

• • system

[15] [22] [26] [10]

[9]

Edge Detection Open algorithm system

Minutiae matching approach

Density map matching and

minutiae-based matching

sparseness

For creating minutiae descriptor

Identify the fingerprint ridges denseness and

\_

To find the ridges existed in the fingerprint image

\_

\_

\_

• •

major factor for fingerprint

representation.

• systems.

No redundancy between both

Low storage cost.

\_

\_

\_

\_

Automatic identityauthentication system

Use the fingerprint to identify person identity.

Its intended mainly for forensic applications account for approximately \$100 million from the

world market.

multimodal biometric

unimodal biometric systems

• •

Recognize person using more than one

biometric property.

Recognition using only one biometric crater.

•

Late to progress in the performance.

• • • • • \_

similarities between the classes

variations within the class.

Contain many noises

Can be faceable

Not universal

multimodal biometric

Unimodal biometric

• •

Using various applications to benefit from

different types of biometrics advantages

Using one single biometric feature.

Minutia Score Matching

method (FRMSM)

**Methods used**

**Reason of application**

Matching the input fingerprint with the stores

fingerprint database.

**Advantages**

\_

•

Reliability due to use the combination of deferent biometric strength.

• •

Varity in the level of difficulty in the

data gained from humans.

• •

Some individuals may not have the

chosen biometric crater.

•

Biometric sign can expose to forgery.

There may be a lot of similarity in the

features sets of the used biometric.

Scanned data became noisy.

**Disadvantages**

\_

