In April 2017, the Intelligence Advanced Research Projects Activity (IARPA) held a dry run for the data collection portion of its Nail to Nail (N2N) Fingerprint Challenge. This data collection event was designed to ensure that the real data collection event held in September 2017 would be successful. To this end, biometric data from unhabituated individuals needed to be collected. That data is now released by NIST as Special Database 301.In total, 14 fingerprint sensors were deployed during the data collection, amassing a series of rolled and plain images. The devices include rolled fingerprints captured by skilled experts from the Federal Bureau of Investigation (FBI) Biometric Training Team. Captures of slaps, palms, and other plain impression fingerprint impressions were additionally recorded. NIST also partnered with the FBI and Schwarz Forensic Enterprises to design activity scenarios in which subjects would likely leave fingerprints on different objects. The activities and associated objects were chosen in order to use a number of latent print development techniques and simulate the types of objects often found in real law enforcement case work. NIST also collected some mugshot-style face and iris images of the subjects who participated in the dry run. These data are also available for download.

In September 2017, the Intelligence Advanced Research Projects Activity (IARPA) held a data collection as part of its Nail to Nail (N2N) Fingerprint Challenge. Participating Challengers deployed devices designed to collect an image of the full nail to nail surface area of a fingerprint equivalent to a rolled fingerprint from an unacclimated user, without assistance from a trained operator. Traditional operator-assisted live-scan rolled fingerprints were also captured, along with assorted other friction ridge live-scan and latent captures. In this data collection, study participants needed to have their fingerprints captured using traditional operator-assisted techniques in order to quantify the performance of the Challenger devices. IARPA invited members of the Federal Bureau of Investigation (FBI) Biometric Training Team to the data collection to perform this task. Each study participant had N2N fingerprint images captured twice, each by a different FBI expert, resulting in two N2N baseline datasets. To ensure the veracity of recorded N2N finger positions in the baseline datasets, Challenge test staff also captured plain fingerprint impressions in a 4-4-2 slap configuration. This capture method refers to simultaneously imaging the index, middle, ring, and little fingers on the right hand, then repeating the process on the left hand, and finishing with the simultaneous capture of the left and right thumbs. This technique is a best practice to ensure finger sequence order, since it is physically challenging for a study participant to change the ordering of fingers when imaging them simultaneously. There were four baseline (two rolled and two slap), eight challenger and ten auxiliary fingerprint sensors deployed during the data collection, amassing a series of rolled and plain images. It was required that the baseline devices achieve 100% acquisition rate, in order to verify the recorded friction ridge generalized positions (FRGPs) and study participant identifiers for other devices. There were no such requirements for Challenger devices. Not all devices were able to achieve 100% acquisition rate. Plain, rolled, and touch-free impression fingerprints were captured from a multitude of devices, as well as sets of plain palm impressions. NIST also partnered with the FBI and Schwarz Forensic Enterprises (SFE) to design activity scenarios in which subjects would likely leave fingerprints on different objects. The activities and associated objects were chosen in order to use a number of latent print development techniques and simulate the types of objects often found in real law enforcement case work.

Fingerprint Database

Dataset comprises 6,000+ fingerprint images from 100 individuals, each paired with 5-7 distorted or latent versions to simulate real-world forensic challenges. It is designed for fingerprint identification, recognition systems, and forensic investigations, offering a robust resource for biometric data analysis, criminal investigations, and automated fingerprint matching. By leveraging this dataset, researchers and law enforcement agencies can enhance fingerprint… See the full description on the dataset page: https://huggingface.co/datasets/UniDataPro/forensic-fingerprint-dataset.

Automated fingerprint identification systems (AFIS) is one type of biometric technology that utilizes digital imaging technology to analyze and compare fingerprints from a stored database. They are commonly used in areas of law enforcement, healthcare, government, among others. In 2022, the AFIS market was valued at **** billion U.S. dollars, and is forecast to grow to ***** billion dollars by 2028.

The LUTBIO database provides a comprehensive resource for research in multimodal biometric authentication, featuring the following key aspects:

• Extensive Biometric Modalities: The database contains data from nine biometric modalities: voice, face, fingerprint, contact-based palmprint, electrocardiogram (ECG), opisthenar (back of hand), ear, contactless palmprint, and periocular region.

• Diverse Demographics: Data were collected from 306 individuals, with a balanced gender distribution of 164 males and 142 females, spanning an age range of 8 to 90 years. This diverse age representation enables analyses across a wide demographic spectrum.

• Representative Population Sampling: Volunteers were recruited from naturally occurring communities, ensuring a large-scale, statistically representative population. The collected data encompass variations observed in real-world environments.

• Support for Multimodal and Cross-Modality Research: LUTBIO provides both contact-based and contactless palmprint data, as well as fingerprint data (from optical images and scans), promoting advancements in multimodal biometric authentication. This resource is designed to guide the development of future multimodal databases.

• Flexible, Decouplable Data: The biometric data in the LUTBIO database are designed to be highly decouplable, enabling independent processing of each modality without loss of information. This flexibility supports both single-modality and multimodal analysis, empowering researchers to optimize, combine, and customize biometric features for specific applications.

✅ Data Availability: If you wish to use the LUTBIO dataset, please download the attached Word document, fill in the information, and send it as an attachment to rykeryang AT 163.com. We will process your request as soon as possible!

🥸 Important Notice: Please read the data collection protocol of the LUTBIO dataset carefully before use, as it is essential for understanding and correctly interpreting the dataset. Thank you.

😎 Good news! Our paper has been accepted by Information Fusion, and the DOI is https://doi.org/10.1016/j.inffus.2025.102945. We appreciate the reviewers and the editor for their efforts.🥰🥰🥰

NIST, working with the FBI, has digitized 888 inked fingerprint arrest cards that were in various physical conditions, from pristine to badly damaged and faded, and were collected during law enforcement professionals' duties. This database contains images of the 10 rolled fingerprint impressions, the two four-finger slap impressions (finger positions 13 and 14), the two thumb slap impressions (finger positions 11 and 12) and the segmented impressions from the slap images (13,14). The database also includes the coordinates that were used to segment the impressions from the slap fingerprint images.The cards were scanned at three different resolutions: 500, 1,000, and 2,000 pixels per inch (PPI). All three resolutions were scanned in grayscale at a depth of 8 bits-per pixel.Data available as of July 2018 is Special Database 300a, in 500 ppi with PNG formatted impressions. Data at other resolutions, in other image formats, and in other record types may be forthcoming.

Local LSS, local LTS, local MCC and local MTM are four algorithms for local matching. D1, D2, D3 and D4 are four sub-databases of FVC2002. D*1, D*2, D*3 and D*4 are four sub-databases of FVC2004.EER results on FVC database for local matching.

2D and 3D Fingerrpint dataset. It was created by former Ph.D. stduent Ms. Wei Zhou under the supervision of Prof. J. Hu who acts as the communication contact., , , # 2D and 3D Fingerprint Dataset

This database consists of 3D fingerprints (2D equivalent ones) collected from 150 subjects (volunteers), so there are in total 150 subfolders.

Description of the data and file structure

For 3D Database:

1. This database consists of 3D fingerprints (2D equivalent ones) collected from 150 subjects (volunteers), so there are in total 150 subfolders.

2. The naming for the samples is SIRE-Subject ID_Finger ID_Capture Order. The Finger IDs are listed below. There are in total 150 volunteers, so the Subject ID ranges from 1 to 150. For each subject, the Finger ID ranges from 1 to 10 accordingly. The Capture Order can be 1 or 2 for 3D fingerprints. For example, the fingerprint image named SIRE-102_3_2.bmp in subfolder 102 represents the second capture of the right middle finger of subject 102. Besides, there are several post-processed images (e.g. SIRE-1_1_1_HT1.bmp, SIRE-1_1_1_R414.bmp) corresponding to each 3D fingerprint image.

3. In the sub subfold...

The size of the Automated Fingerprint Identification System Market market was valued at USD 16.47 Billion in 2023 and is projected to reach USD 56.81 Billion by 2032, with an expected CAGR of 19.35% during the forecast period. Recent developments include: April 2023: The national database authority of Pakistan has introduced the impressively accurate automatic fingerprint identification system (AFIS), which was locally designed. Software developers from the National Database & Registration Authority created the system, which they have named "Nadir" (the Urdu word for "unique"). The automated system is expected to revolutionize how biometric identification is used in a variety of civil applications, including immigration, border control, e-governance, and social services. NADIR has attained an impressive accuracy rate above 99.5% based on the internationally renowned Fingerprint Verification Competition (FVC), a benchmarking exercise conducted in Italy. As a public service, NADRA can now reliably and swiftly store fingerprints & identify people for a variety of uses., According to the statement, NADRA's status as a pioneer in cutting-edge identity management solutions has been cemented with the introduction of the system. As a result of this breakthrough, Pakistan has now joined some countries who have developed their original AFIS technology and is prepared to sell its product on the global market to assist other nations in improving their identification procedures. The worldwide market for biometric identification technology, according to authority authorities, is mostly dominated by suppliers from industrialized nations including the US, Russia, Japan, the UK, France, Germany, & others., Ijazat Aap Ki, a latest data protection service that guarantees the security and privacy of citizen data, was introduced by NADRA in March. The first data protection service in Pakistan sends a 6-digit passcode to individuals' phones whenever a request is made for a transaction or personal information, giving users more control over their data and limiting unlawful access to the service providers, including banks., March 2022: Suprema launched a new generation of credentials control products that concentrates heavily on contactless solutions. The star of Suprema's production was BioStation 3, an all-in-one access control solution that delivers numerous credential options, from facial recognition and mobile access to barcodes, QR codes, and RFID cards. BioStation 3 will be emitted in the second half of the year., November 2021: Suprema announced the successful integration of its biometric access control products with Genetec Security Center, a unified security platform that connects security systems, sensors, and data in a single intuitive interface.. Notable trends are: Growing government initiatives are driving the market growth.

The global Automated Fingerprint Identification market will expand significantly by XX% CAGR between 2024 and 2030.

There is an increase in demand for biometric systems because it increases the safety of people and the frequency of cyber threats. It also gives access to only those who have the identification and safeguards the information so that misuse of data is reduced. One of the main reasons is for security purposes and it is used by the government which is a key driver. Another key factor is the issue of privacy is resolved and more safeguarding of data is done.
This market serves a diverse range of applications, including national security, law enforcement, enterprise and e-governance, personal information and business transactions, and others.
The global biometric system market, with its high security features, quick integration, and ease of installation, is critical in protecting important assets such as ATMs,smart cards, mobile devices, and computer and network access.

Market Dynamics of the Automated Fingerprint Identification System Market:

Key Drivers of the market

Initiatives by the different governments are accelerating the growth of the market

The automated fingerprint identification system is widely used and promoted by the government for various reasons. One of the main reasons is for security purposes. Terrorism and crime rates have increased over the past years. For instance, The US National Strategy to Combat Terrorist Travel prioritizes biometric technology to detect and prevent suspected terrorists from entering the US. The policy aims to support foreign governments in deploying biometric technologies. The AFIS has escalated as it is used in this field for the recognition of people. https://www.state.gov/reports/country-reports-on-terrorism-2022/As there are different initiatives from the governments in terms of banking security and law enforcement, other private institutions also apply this system to their organizations for security reasons and so the demand for this identification system has risen. Initiatives like unique identity cards for every citizen with the verification of biometrics are compulsory so that citizen’s data is stored. For Instance, the Adhar card initiative by the Indian government collects, stores, and identifies data. With this, the NAFIS is a searchable database of crime and criminal-related fingerprints, and it covers all of India. It is overseen by the Central Fingerprint Bureau (NCRB) of the National Crime Records Bureau (NCRB), which is situated in New Delhi. The web-based application's primary goal is to gather fingerprint information from every criminal from every state and the Union Territories. Across the globe, the citizen's database is stored for reasons like National ID programs and voter registration. National ID for the identification of the citizen in the country. To perform a transparent voting process, transparent elections need to take place and AFIS helps by reducing fraud. AFIS is used to guarantee that welfare benefits are consistently distributed to the correct recipients. Governments can reduce the possibility of duplication in the provision of necessary services and subsidies by providing recipients with unique identification. For Instance, Governmental programs like the Philippines National Police (PNP) and Ghana's NIS automated fingerprint identification systems demonstrate the system's broad applicability for biometric identification needs. (Source:https://www.nec.com/en/press/201507/global_20150722_02.html)Furthermore, biometrics are critical for tackling the issues of identity management in large-scale systems. Biometric data is being used by governments and corporations to authenticate identities, including border control, issuing official documents, and monitoring employee access.

Rise in demand in the banking and financial sector for security purposes

The banking industry, which is distinguished by its increased focus on safe financial transactions, is depending more and more on AFIS. Financial transactions are made easier and more secure thanks to this technology, which also guarantees dependability and efficiency. The banking industries are increasingly adopting automated fingerprint identification system technologies to maintain privacy and security while facilitating speedy and secure financial transactions. For example, in banking, biometrics refers to...

Automated Fingerprint Identification System Market size was valued at USD 14.67 Billion in 2024 and is projected to reach USD 67.85 Billion by 2031, growing at a CAGR of 21.1% during the forecast period 2024-2031.Global Automated Fingerprint Identification System Market DriversGrowing Fears Regarding Security: Robust and dependable identification systems are more important than ever due to the increase in threats to international security. AFIS is being used by governments and law enforcement organizations more frequently in an effort to improve national security and expedite the criminal identification process. Accurate person identification is aided by AFIS, which is essential for both deterring and solving crimes.Developments in Technology: Rapid biometric technology improvements are helping the AFIS business. The accuracy and efficiency of AFIS have increased due to advancements in algorithmic processing, image technologies, and fingerprint sensors. Due to the decrease in false match rates and processing times brought about by these technological developments, AFIS is now a more appealing choice for a wider range of applications.Regulations and Initiatives by the Government: Numerous nations are taking steps to enhance border control procedures and national identity systems. For instance, AFIS is largely used for identity verification in projects like India's Aadhaar, which is one of the biggest biometric databases worldwide. The use of more secure identification systems is also being pushed by international standards and regulations pertaining to biometric data, which is driving the AFIS industry.Growing Acceptance in Legal Uses: AFS is being utilized more frequently for civil applications including voter registration, national ID programs, and immigration control in addition to criminal identification. For these kinds of applications, AFIS is perfect because it can handle big databases and offer prompt and precise identification. The market is expanding rapidly as a result of this wider usage in a number of industries.

Fingerprint_TF

Deep Learning fingerprint recognition using Tensorflow2.

Image Information

Fingerprint image size is 160x160(500DPI).

GitHub

https://github.com/JinZhuXing/Fingerprint_TF

SM, ECM and MTM are three algorithms for fingerprint matching. D1, D2, D3 and D4 are four sub-databases of FVC2002. D*1, D*2, D*3and D*4 are four sub-databases of FVC2004.Comparative results between MTM and previous papers.

Global Biometric Technology Market size is set to expand from $ 48.48 Billion in 2023 to $ 157.64 Billion by 2032, with an anticipated CAGR of around 14% from 2024 to 2032.

Footnotes: Abbreviations; Tht  =  Theoretical, Obs  =  Observed. aMatches a  =  Number of peptides matched with protein in MS/MS query. bSequence coverage b  =  Total percentage of proteins amino acid sequence covered by peptides in MS/MS analysis. cMASCOT score c =  >40 indicate identification or extensive homology (p

This is a subset of the original Sokoto Coventry Fingerprint Dataset (SOCOFing), which is a biometric fingerprint database designed for academic research purposes.

The Original SOCOFing is made up of 6,000 fingerprint images from 600 African subjects and contains unique attributes such as labels for gender, hand and finger name as well as synthetically altered versions with three different levels of alteration for obliteration, central rotation, and z-cut. For a complete formal description and usage policy please refer to the following paper: https://arxiv.org/abs/1807.10609

This modified version eliminates the "Altered" directory and classifies the fingerprint images into separate classes (e.g. 100_M, 101_M, etc.) based on their subjects, in the "Real" directory…

SM, ECM and MTM are three algorithms for fingerprint matching. This table shows the average matching time (ms) for per match on FVC2004-DB1.Time between MTM and previous papers.

Citing - DOI: 10.1109/ICPR48806.2021.9412304 - https://ieeexplore.ieee.org/document/9412304 - Video presentation: https://youtu.be/AueL2WUEjD4

L3-SF - A public database of L3 synthetic fingerprint images with five subsets of 148 identities, with 10 samples per identity, totaling 7400 fingerprint images. - We include sweat pore annotations for 740 images to assist in pore detection research. - The synthetic fingerprints contain L3 traits, such as distinct ridge contours and incipient ridges, features that increase the reliability of fingerprint recognition. - Huge texture improvement on the fingerprint images. - Scratches on fingerprint images.

Authors - André Brasil Vieira Wyzykowski - Mauricio Pamplona Segundo - Rubisley de Paula Lemes

Abstract

A reliable and comprehensive public WiFi fingerprinting database for researchers to implement and compare the indoor localization’s methods.The database contains RSSI information from 6 APs conducted in different days with the support of autonomous robot.

We use an autonomous robot to collect the WiFi fingerprint data. Our 3-wheel robot has multiple sensors including wheel odometer, an inertial measurement unit (IMU), a LIDAR, sonar sensors and a color and depth (RGB-D) camera. The robot can navigate to a target location to collect WiFi fingerprints automatically. The localization accuracy of the robot is 0.07 m ± 0.02 m. The dimension of the area is 21 m × 16 m. It has three long corridors. There are six APs and five of them provide two distinct MAC address for 2.4- and 5-GHz communications channels, respectively, except for one that only operates on 2.4-GHz frequency. There is one router can provide CSI information. Instructions:

Database Folder name "RSSI_6AP_Experiments" which includes:

• Nexus 4 database

• Nexus 5 database

Training & Testing data are seperated & collected in different time with different locations.

• The general format for csv data file is:

-- X & Y & The list of RSSI

-- X | Y | RSSI Vector

For the papers https://ieeexplore.ieee.org/document/8485369 https://ieeexplore.ieee.org/document/8830368 https://ieeexplore.ieee.org/document/8988252

Fingerprint Latent Matching Software Market Outlook

According to our latest research, the global fingerprint latent matching software market size reached USD 2.1 billion in 2024, driven by increasing adoption across forensic, governmental, and financial sectors. The market is projected to grow at a CAGR of 13.4% from 2025 to 2033, reaching a forecasted value of USD 6.5 billion by 2033. This robust growth trajectory is primarily fueled by the rising demand for advanced biometric solutions to enhance identity verification and security processes, alongside technological advancements in artificial intelligence and machine learning algorithms that significantly improve matching accuracy and speed.

One of the primary growth factors for the fingerprint latent matching software market is the increasing incidence of cybercrime and identity theft globally. As digital transformation accelerates across industries, the need for robust authentication mechanisms has become more pronounced. Law enforcement agencies, in particular, are leveraging advanced fingerprint latent matching solutions to solve criminal cases more efficiently, leveraging vast databases and real-time analytics. Additionally, the banking and finance sector is integrating these solutions to bolster fraud prevention measures and comply with stringent regulatory standards. The convergence of biometric authentication with digital banking and fintech platforms is further amplifying the demand for sophisticated fingerprint matching technologies, as institutions strive to provide secure and seamless customer experiences.

Another significant growth driver is the rapid advancements in artificial intelligence (AI) and deep learning technologies. Modern fingerprint latent matching software now incorporates AI-driven algorithms that dramatically enhance the accuracy and reliability of fingerprint analysis, even with partial or degraded prints. This technological leap has expanded the application of fingerprint matching beyond traditional law enforcement to sectors such as healthcare, where patient identification and data integrity are critical. Moreover, the proliferation of mobile and cloud-based biometric solutions is making fingerprint matching more accessible and scalable, enabling organizations of all sizes to leverage these tools for secure access control, workforce management, and patient verification. As AI continues to evolve, the market is expected to witness further innovation, with solutions offering faster processing times, lower error rates, and improved interoperability across diverse systems.

The implementation of stringent government regulations and national ID programs is also playing a pivotal role in driving market growth. Governments worldwide are investing heavily in biometric infrastructure to enhance border security, streamline citizen services, and combat identity fraud. National identification initiatives, e-passports, and voter registration systems are increasingly relying on fingerprint latent matching software to ensure the authenticity and uniqueness of individuals. This trend is particularly prominent in emerging economies, where digital identity programs are being rolled out at scale. Furthermore, the integration of fingerprint matching with other biometric modalities, such as facial and iris recognition, is creating multi-layered security frameworks that are highly effective in high-stakes environments. The synergy between regulatory mandates and technological innovation is thus creating a fertile ground for sustained market expansion.

Regionally, North America continues to dominate the fingerprint latent matching software market, supported by substantial investments in law enforcement technology and widespread adoption across financial and healthcare sectors. The region's mature digital infrastructure and proactive regulatory environment have accelerated the deployment of advanced biometric solutions. Meanwhile, Asia Pacific is emerging as the fastest-growing market, driven by large-scale government initiatives, rapid urbanization, and increasing digitalization across industries. Europe and the Middle East & Africa are also witnessing steady growth, fueled by rising security concerns and the implementation of national identification programs. The global landscape is marked by a dynamic interplay of technological innovation, regulatory frameworks, and evolving security challenges, shaping the future trajectory of the fingerprint latent matching software market.