Publications by authors named "Arnaud Bletterer"
Article Synopsis
- Developing an automatic acne grading system using machine learning requires extensive data and labeling, but the authors created a model that performs well on low-resolution images from fewer patients with uneven acne severity distribution.
- The study utilized 1,374 paired images from 391 patients, expertly labeled, to train a deep learning model which achieved 66.67% accuracy on the test set.
- The results suggest that this model can be a viable tool for medical practitioners and provide standardized assessments for patients, highlighting its potential despite limited data.
A Local Graph-Based Structure for Processing Gigantic Aggregated 3D Point Clouds.
IEEE Trans Vis Comput Graph
August 2022
We present an original workflow for structuring a point cloud generated from several scans. Our representation is based on a set of local graphs. Each graph is constructed from the depth map provided by each scan.
View Article and Find Full Text PDF