master Assignment
Heritage Biometrics artist profiling from 3D fingerprints
Type: Master EE/M/CS
Student: Unassigned
Duration: TBD (min. 6 months/fulltime)
If you are interested please contact:
Background:
In the fine arts like sculpting, an artist would often leave her or his impressions on fresh and wet clay in the act of modeling the artwork. When clay is fired in a kiln, it becomes solid and water-resistant. Every trace left on it can remain unchanged for centuries. In controlled settings, fingerprints left on clay have not been investigated thoroughly yet. This means that there are many gaps to be filled in the acquisition setups as well as in the image processing step.
Goals:
1) Using the equipment from the DMB Lab, the student will design a 3D high-resolution acquisition system that captures fingerprints left on plasticine at different conditions (e.g., wet, dry, complete, partial).
2) The student will implement a 3D-to-2D unwrapping algorithm of the acquired 3D fingerprints and compare such unrolled fingerprints with the flat ones in terms of feature extraction and fingerprint matching.
DMB Lab:
The Data Management & Biometrics Lab has the following depth camera’s available:
- Intel real sense (older models) (structured light); xbox 360 kinect v1 (structured light) https://all3dp.com/2/kinect-3d-scanner-easy-beginner-tutorial/
- Arducam (tof) https://www.arducam.com/time-of-flight-camera-raspberry-pi/
- Artec Eva (structured Light) https://www.artec3d.com/portable-3d-scanners/artec-eva
Supervisor: Dzemila Sero (assistant professor DMB)
Co-supervisor: Bieke van der Mark (art historian and curator, Rijksmuseum)
Your profile:
You are a graduate student with a strong experience in Computer Vision and Machine Learning. You should be a capable programmer with prior experience of using python or Matlab. Part of the project requires critical thinking and exploring new directions, so you will also have the opportunity to go beyond current approaches.
Why join?
- Be part of a high-impact project that has the potential to substantially contribute to heritage science.
- Work at the intersection of machine learning, computer vision, conservation, and art history.
- Collaborate with a team of interdisciplinary experts of engineers and computer scientists.
Who Should Apply?
- Students with a strong background in machine learning and computer vision. Affinity or interest in the world of decorative arts is expected.
- Enthusiasts of computer vision for decorative arts, seeking to make a tangible impact in heritage science.
References:
- Sero, Dzemila, et al. "The study of three-dimensional fingerprint recognition in cultural heritage: Trends and challenges." Journal on Computing and Cultural Heritage (JOCCH) 14.4 (2021): 1-20.
- Sero, Dzemila, et al. "Artist profiling using micro-CT scanning of a Rijksmuseum terracotta sculpture." Science Advances 9.38 (2023): eadg6073.
- Chen, Yi, et al. "3D touchless fingerprints: Compatibility with legacy rolled images." 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference. IEEE, 2006.