Current MS Students

1. Noam Polak
2. Alex Saraev
3. Ron Sukner
4. Eden Meerov

Data+ 2026 (Duke): Unveiling Hidden Inscriptions under a 700-Year-Old Painting

We develop advanced tools to recover hidden text from the reverse side of a 13th-century illuminated manuscript that has been glued to cardboard. By leveraging hyperspectral imaging and develop machine learning tools, our goal is to unveil secrets that have been obscured for 700 years.To achieve this, our study introduces an innovative pipeline that applies high-dimensional separation models to decipher text hidden beneath different pigments, relying on ideas of manifold learning in high and low dimensions. This approach integrates image processing, spectral data analysis, and NLP to bring these ancient words back to light.

      
 Kyra Pahwa 

 Ronit Dey

 Frank Xie

Johan Gael Nino Espino

Alumni students

Shufan Xia, Duke University, Manifold learning using Wasserstein distance: The Maya codex, 15th century, as a case study

(now a PhD student at Stanford University)

Rui Xin, Duke University, Study the Geometry of the Shape Space Using Horizontal Diffusions with Applications to Evolutionary Anthropology

(now a PhD student in Computer Science at University of Washington.)

Alex Winn, Duke University, Improving Registration in Shape Space.
 

Wallace Peaslee, Duke University, Enhancing Underdrawing Legibility with Hyperspectral Imaging Data from a 15th-Century Painting

(now PhD student in Department of Applied Mathematics and Theoretical Physics, University of Cambridge.)

Ohr Dallal, MS student, Tel Aviv University, Israel, Leaning to Cluster Multispectral Signatures from multispectral weakly annotated imaging

Nick Chakraborty, Duke University, Geometry and Sampling Adaptive Manifold Reconstruction from Noisy Scattered Points

(now a PhD student at Stony Brook University)