IIITD SMARTPHONE FINGER-SELFIE DATABASE V2
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:
- White Background
- Natural Background
- 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 database, email the duly filled license agreement to email@example.com 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.
- The 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.
- Executable and Features: Toolboxes for segmentation and enhancement, and DSN Features can be downloaded from: LINK. To obtain the password for the file, email the duly filled license agreement to firstname.lastname@example.org with the subject line "License agreement for files of On Matching Finger-selfies using Deep Scattering Networks"