North America

Automatic Labeling of Facial zones for Digital Clinical application: An ensemble of Semantic Segmentation Models via Pubmed

Skin Res Technol. 2024 Feb;30(2):e13625. doi: 10.1111/srt.13625.

Rafael Tuazon 1 , Siavash Mortezavi 1

The application of artificial intelligence to facial aesthetics has been limited by the inability to discern facial zones of interest, as defined by complex facial musculature and underlying structures. Although semantic segmentation models (SSMs) could potentially overcome this limitation, existing facial SSMs distinguish only three to nine facial zones of interest.

Because some zones overlap, some pixels are included in multiple zones, violating the one-to-one relationship between a given pixel and a specific class (zone) required for SSMs. The full facial zone model was therefore used to create three sub-models, each with completely non-overlapping zones, generating three outputs for each input image that can be treated as standalone models. For each facial zone, the output demonstrating the best Intersection Over Union (IOU) value was selected as the winning prediction.

The new SSM demonstrates mean IOU values superior to manual annotation and landmark analyses, and it is more robust than landmark methods in handling variances in facial shape and structure.

Read more

Recent Posts

FOCUS#12: Testing expert discussion around biomechanical properties

The FOCUS #12 is here, with all you need to know about expert discussion around…

Skin Mechanical Integrity: In Vitro Tools and the Role of the Extracellular Matrix by Skinobs via FOCUS#12

The skin is subject to constant mechanical stresses, including stretch and compression due to body…

Biomechanical Properties and the Skin: Implications for Cosmetic Science by Skinobs via FOCUS#12

As the body’s largest organ, the human skin serves a multitude of physiological functions, such…