Wojciech Michal Matkowski, Tingting Chai and Adams Wai Kin Kong. “Palmprint Recognition in Uncontrolled and Uncooperative Environment.” IEEE Transactions on Information Forensics and Security, vol. 15, pp 1601-1615, 2019, DOI: 10.1109/TIFS.2019.2945183.
Preprint can be found now on arXiv here
Paper can be found on IEEE Xplore here
To acquire the NTU Palmprints from the Internet (NTU-PI-v1) database (which was used in the paper), download and fill in the "Data Release Agreement.pdf" file. Print the agreement and sign on page 2. Scan the signed copy and send back to maskotky@gmail.com, and adamskong@ntu.edu.sg with title "Application for NTU Palmprints from the Internet database (NTU-PI-v1)". A download link to the database will be send to you once after we receive the signed agreement file.
Example images from NTU-PI-v1. Images in the same column are from the same palm. Images are resized to the same size.
Examples of original images downloaded from the Internet. Hands are higlited in red boxes in the original images.
- download matconvnet here unpack and put into maltab folder
- download pretrained alignemnt network (ROI-LAnet) here and put into preTrainedNetworks folder
- download pretrained end to end network (EE-PRnet) here and put into preTrainedNetworks folder
- see and run demo codes in ROI-LAnet and EE-PRnet folders
If you have any questions about the paper please email me on maskotky@gmail.com It is realtively easy to implement it in pytorch. On some special request I would be also able to share some pytroch codes. For significant improvements and pytorch impelmentation see here