Biometric authentication during the COVID-19 and post-pandemic times require a touchless authentication mechanism. While existing studies showcase the use of fingerphoto for touchless authentication, a short video of the finger can provide many good-quality frames. This research presents the first publicly available finger-video dataset, titled Multi-Movement Finger-Video (MMFV) Database. The MMFV dataset has 3792 videos from 336 classes, acquired over two sessions, and spans three different movement types (pitch, yaw, and roll).

• The database can be downloaded from the following link: MMFV: Multi-Movement Finger-Video Database
• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for MMFV: Multi-Movement Finger-Video Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
• This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• i) A. Malhotra, M. Vatsa, and R. Singh, MMFV: A Multi-Movement Finger-Video Database for Contactless Fingerprint Recognition. IEEE International Workshop on Biometrics and Forensics (IWBF), pp. 1-6, 2023.
• ii) A. Malhotra, A. Sankaran, M. Vatsa, & R. Singh. On matching finger-selfies using deep scattering networks. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2(4), 350-362, 2020.

Users post images on Social media, highlighting miniature objects holding in their hands. These posts may contain fingers in the uploaded photograph. Few of these photographs also contain clearly visible ridge-valley details. Using hashtags #miniature, #myhand, and #finger, we collect Social-Media Posted Finger-selfie (SMPF) database. The database consists of 1,000 images, each of which is collected from public Instagram posts. These images are handpicked so that ridge-valley details in proximal phalanx is visible.

• The database can be downloaded from the following link.

Social-Media Posted Finger-selfie (SMPF) Database

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Social-Media Posted Finger-selfie (SMPF) Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Malhotra, S. Chhabra M. Vatsa, and R. Singh. On Privacy Preserving Anonymization of Finger-selfies, In IEEE Computer Vision and Pattern Recognition Workshop on Fair, Data Efficient and Trusted Computer Vision, 2020.
• A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh. On smartphone camera based fingerphoto authentication, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, pages 1-7, 2015.

IIITD SmartPhone Finger-selfie Database v2 (ISPFDv2) consists of more than 17,000 finger-selfies and 2432 livescan fingerprint images obtained from 304 unique fingers. The finger-selfie images are taken using two smartphones: OnePlus One (OPO) and Micromax Canvas Knight, while, livescan fingerprints are acquired using Secugen Hamster IV at 500 PPI. Indoor images are captured in both constrained and uncontrolled environments, while in outdoor conditions, images are captured without flash during daylight and with flash during the night. Auto-focus is always kept at ON status. Based on the challenges considered, the database is divided into four subsets. The four subsets are:

1. White Background
2. Natural Background
3. Resolution
4. Cross-domain (Livescan fingerprints)

• DATABASE: IIITD SmartPhone Finger-selfie Database v2 (ISPFDv2) (17.7 GB)

(CRC32: 8FC52A33,
MD5: CB41E0A3FD8D4CF9DCE6E0DEC5D5C9B1,
SHA-1: BBD3F3EC872AA0BAFEC503A77359006B1536B95F)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for IIITD SmartPhone Finger-selfie Database v2 (ISPFDv2)"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh. On smartphone camera based fingerphoto authentication, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, pages 1-7, 2015.
• A. Malhotra, A. Sankaran, M. Vatsa, and R. Singh. On Matching Finger-selfies using Deep Scattering Networks, 2020.

IIITD SmartPhone Fingerphoto Database v1 (ISPFDv1) consists of fingerphotos and live scan images captured using Lumidgm Sensor. It has data for 64 subjects, collected for both right index and right middle finger, hence making a total of 128 classes. This database covers illumination and background variation challenges.

• The database can be downloaded from the following link.

IIITD SmartPhone Fingerphoto Database v1 (ISPFDv1) (7.08GB)

(CRC32:8B44112E, MD5:6F58AAC3EB2691A1D188D1857FB623A3,
SHA-1:E277F9129A885582232F0264FEF93565B9A682AB)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for SmartPhone Fingerphoto Database V1 (ISPFDv1)"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh. On smartphone camera based fingerphoto authentication, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, pages 1-7, 2015.

The appearance of latent fingerprints varies significantly due to the development techniques, leading to large intra-class variation. We propose a Multi-Surface Multi-Technique (MUST) Latent Fingerprint Database. The database consists of more than 16,000 latent fingerprint impressions from 120 unique classes (120 fingers from 12 participants). Including corresponding exemplar fingerprints (livescan and rolled) and extended gallery, the dataset has nearly 21,000 impressions. It has latent fingerprints acquired under 35 different scenarios and an additional four subsets of exemplar prints captured using live scan sensor and inked-rolled prints. With 39 different subsets, the database illustrates intra-class variations in latent fingerprints. The database has the potential usage towards building robust algorithms for latent fingerprint enhancement, segmentation, comparison, and multi-task learning. We also provide annotations for manually marked minutiae, acquisition PPI, and semantic segmentation masks are also provided.

• The database can be downloaded from the following link.

Multi-Surface Multi-Technique (MUST) Latent Fingerprint Database

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Multi-Surface Multi-Technique (MUST) Latent Fingerprint Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Malhotra, M. Vatsa, R. Singh, K. B. Morris, A. Noore, Multi-Surface Multi-Technique (MUST) Latent Fingerprint Database. IEEE Transactions on Information Forensics and Security, 2023.

The Unconstrained Fingerphoto Database (UNFIT database) consists of fingerphotos captured using 45 different smartphones. It has data for 115 subjects, collected for both index and middle finger, separately and together. Hence, there are a total of 230 classes. This database covers many challenges present in a real-world unconstrained environment such as illumination, motion blur, affine variations, and optional usage of the camera flash. The database also includes ground truth annotations of the location of the finger(s).

• The database can be downloaded from the following link.

Unconstrained Fingerphoto Database (UNFIT) (12.3 GB)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Unconstrained Fingerphoto Database (UNFIT)"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• S. Chopra, A. Malhotra, M. Vatsa, and R. Singh. Unconstrained Fingerphoto Database, In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) on Biometrics, 2018.

Children Multimodal Biometric Database (CMBD) consists of iris, fingerprint, and face images of over 100 children (age range of 18 months to 4 years), acquired over two sessions. The iris images are captured using Cross-Match iris scanner, fingerprints are captured using Cross-Match L-scan slap fingerprint scanner and face images are captured using Nikon D90 DSLR. It has data for 106 across both the session and for all 3 modalities. However, to protect the identities of the participants, we have provided iris and fingerprint images only.

• The database can be downloaded from the following link.

Children Multimodal Biometric Database (CMBD) (760MB)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Children Multimodal Biometric Database (CMBD) Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• P. Basak, S. De, M. Agarwal, A. Malhotra, R. Singh, and M. Vatsa. Multimodal Biometric Recognition for Toddlers and Pre-School Children, In IEEE International Joint Conference On Biometrics, 2017..

Spoofed Fingerphoto Database consists of spoofed fingerphotos images captured using OnePlus One and Nokia while spoofed using iPad, Laptop, Nexus and printout. It has data for 128 classes (64 subjects * 2 fingers). This database contains spoofed images across 2 illumination variations and 2 background variations.

• The database can be downloaded from the following link.

Spoofed Fingerphoto Database (1.05GB)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Spoofed Fingerphoto Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Taneja, A. Tayal, A. Malhotra, A. Sankaran, M. Vatsa, and R. Singh, Fingerphoto Spoofing in Mobile Devices: A Preliminary Study, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, 2016.
• A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh. On smartphone camera based fingerphoto authentication, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, pages 1-7, 2015.

The Rural Indian Fingerprint Database comprises images captured from both rural and urban population of India.

• Download link (389MB)
  (CRC32: 172A5837,
  MD5: BAC30E8C9CFC67C68336F13007677C28,
  SHA-1: 7B4B9B1D727CD2E3CA1A8E96A5B4CA9E05AAEDEA)
• To obtain the password for the compressed file, email the duly filled license agreementt to databases@iab-rubric.org with the subject line "License agreement for Social-Media Posted Finger-selfie (SMPF) Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• C. Puri, K. Narang, A. Tiwari, M. Vatsa, and R. Singh, On Analysis of Rural and Urban Indian Fingerprint Images, In Proceedings of International Conference on Ethics and Policy of Biometrics and International Data Sharing, 2010.

Coming Soon.

IIITD Multi-surface Latent Fingerprint Database (IIITD MSLFD) consists of 551 latent fingerprints from 51 subjects lifted from eight different surfaces. The eight surfaces are: 1) Ceramic plate, 2) Ceramic mug, 3) Transparent glass, 4) Steel glass, 5) Compact disc, 6) Compact disc mailer (CD mailer), 7) Paperback book cover, and 8) Hardbound book cover. The corresponding slap fingerprint (4+4+2 prints) gallery images are captured using CrossMatch L-Scan Patrol at 500 dpi.

• The database can be downloaded from the following link.

IIITD Multi-surface Latent Fingerprint Database (IIITD MSLFD) (9.15GB)

(CRC: 64d9da6a,
MD5: f4f55658996efcee49a6947134682db5,
SHA-1: 7ef5c7539a8da8d8b951be87aad794be4fa85302)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "IIITD Multi-surface Latent Fingerprint Database (IIITD MSLFD)"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Sankaran, A. Agarwal, R. Keshari, S. Ghosh, A. Sharma, M. Vatsa, and R. Singh, Latent Fingerprint from Multiple Surfaces: Database and Quality Analysis, In Proceedings of IEEE International Conference on Biometrics: Theory, Applications and Systems, 2015.

IIIT-D MOLF database has 19,200 fingerprints collected using from 100 subjects using five different capture methods: (i) Lumidigm Venus IP65 Shell, (ii) Secugen Hamster-IV, (iii) CrossMatch L-Scan Patrol, (iv) Latent fingerprints, and (v) simultaneous latent fingerprints lifted using black powder dusting process. The details of the database are given below:

Sample Images

Structure

The database is organized in six folders - DB1, DB2, DB3, DB3_A, DB4, DB5. ALl fingerprints are available in compressed WSQ format and in uncompressed BMP format. The total size of the database in WSQ is 600 MB and in BMP format is 21.2 GB. The image size of fingerprints in different subsets of the database and the nomenclature used for naming the images are shown in the table below:

Citation

This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:

• A. Sankaran, M. Vatsa and R. Singh, Multisensor Optical and Latent Fingerprint Database, IEEE Access, 2015.

Download

• WSQ Format: MOLF Database (548MB)

(CRC: E4AD31E7,
MD5: 253b6e27e6c8ddeef22944a4a29cdf39,
SHA-1: D7778CE6FBD86A6C94FD77C890E79A4460D8A2EC)

• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for MOLF Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  The dataset is also available in BMP format (21.2GB). The manual annotation of latent fingerprint is also available. Please write to databases@iab-rubric.org to be able to gain access to these data.

Simultaneous Latent Fingerprint(SLF) Database consists of simultaneous latent fingerprint of 15 subject along with their mated 500ppi optical slap fingerprints. Simultaneous latent fingerprint are obtained using black powder dusting technique with a plain tile as background. Optical fingerprints are captured using Crossmatch LScan Patrol.

The database can be downloaded from the following link.

• IIIT-D SLF Database (690MB)
  (CRC32: F4E41CCE,
  MD5: 61CA12E724CCBD6EB95C8058EC00D01A,
  SHA-1: 2CF1A9C75901195BE1E93369593395C339DDFC6D)
• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Social-Media Posted Finger-selfie (SMPF) Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Sankaran, M. Vatsa, and R. Singh, Hierarchical Fusion for Matching Simultaneous Latent Fingerprint, In Proceedings of International Conference on Biometrics: Theory, Applications and Systems, 2012.

The IIIT-D latent fingerprint database is an exclusive database consisting of only latent fingerprint impressions of all 10 fingers of 15 subjects. Multiple instances are captured for every fingerprint, enabling latent to latent fingerprint comparison. The latent fingerprints are lifted from two different backgrounds - card and tile- trying to simulate different environments from which they are lifted. Also, the dryness of the skin friction ridge is varied to obtain multiple impressions of varying quality and information. There are in total 1046 latent fingerprints. Mated 500ppi and 1000ppi fingerprint sensor images are available. The 500ppi are slap images captured using Crossmatch L1scan. The 1000ppi images are captured using SecuGen Hamster IV. This database is made public to facilitate researchers to publish results over a common database.

The database can be downloaded from the following link.

• Specifications of the Latent database (57KB)
• IIIT-D Latent Fingerprint Database (6.1GB)
  (CRC32: 2B48F463,
  MD5: 0926FCC705DF8357E0BA7EF3522ECC2C,
  SHA-1: BA7C58649617256C7E5665BDD47C24AAC2349DC7)
• IIIT-D Latent_Mated_500ppi Fingerprint Database (11MB)
  (CRC32: 7B551585,
  MD5: 07B0A6DB443BCAD7DCEC419447219D81,
  SHA-1: 4A0822CACBA79D3A9E0CE45AD738F02998CF4AF5)
• IIIT-D Latent_Mated_1000ppi Fingerprint Database (33MB)
  (CRC32: 2FEA5E26, MD5: AAF96CCB875C1B42ABD1A1A8592A5AA5,
  SHA-1: FF9AE26B6EAD12C365CCAC82429DFE1C82D41F42)
• To obtain the password for the compressed file, email the duly filled license agreement to databases@iab-rubric.org with the subject line "License agreement for Social-Media Posted Finger-selfie (SMPF) Database"
  NOTE: The license agreement has to be signed by someone having the legal authority to sign on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
  This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following paper:
• A. Sankaran, T.I. Dhamecha, M. Vatsa, and R. Singh, On Matching Latent to Latent Fingerprints, In Proceedings of International Joint Conference on Biometrics, 2011.