Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans

Hati, Avik; Bustreo, Matteo; Sona, Diego; Murino, Vittorio; Bue, Alessio Del

doi:10.1109/icpr48806.2021.9412513

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, in archaeology, the problem is less well-studied, and the techniques available are less sophisticated. For example, Hati et al [5] segmented an entire human mummy into jewels, body, bandages, and the wooden support frame, using a combination of voxel intensity and the manual selection of geodesic shapes. Low resolution volumetric scans of mummies were considered in [6,7], with segmentation performed one slice at a time using classical machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Automated segmentation of microtomography imaging of Egyptian mummies

Tanti,

Berruyer,

Tafforeau

et al. 2021

Preprint

View full text Add to dashboard Cite

Propagation Phase Contrast Synchrotron Microtomography (PPC-SRµCT) is the gold standard for non-invasive and non-destructive access to internal structures of archaeological remains. In this analysis, the virtual specimen needs to be segmented to separate different parts or materials, a process that normally requires considerable human effort. In the Automated SEgmentation of Microtomography Imaging (ASEMI) project, we developed a tool to automatically segment these volumetric images, using manually segmented samples to tune and train a machine learning model. For a set of four specimens of ancient Egyptian animal mummies we achieve an overall accuracy of 94-98% when compared with manually segmented slices, approaching the results of off-the-shelf commercial software using deep learning (97-99%) at much lower complexity. A qualitative analysis of the segmented output shows that our results are close in term of usability to those from deep learning, justifying the use of these techniques.

show abstract

Section: Introductionmentioning

confidence: 99%