We are pleased to announce that the results of our work on ASEMI have been published on PLOS ONE. This includes a technical description of the tool we developed to automatically perform the laborious process of segmenting the scanned volumes into the various component materials, such as textiles, organic tissues, balm resin, ceramics, and bones. Using the developed software, the human specialist only needs to manually segment a small sample of the volumetric image. This is used to train and automatically optimise a machine learning system, which can then segment the whole volume in a fraction of the time previously required. The accuracy obtained by the ASEMI segmenter approaches the results of off-the-shelf commercial software using deep learning, at a much lower complexity. Following the principles of “Open Innovation, Open Science, Open to the World”, the developed algorithms, data sets, and results have been made freely available to the general public.
Links: Paper, Git Repository, Data Sets
