The non-commercial version of MORPH-II (released in 2008) is the standard used in research .
The data includes a diverse representation of age, gender, and ethnicity. morph ii dataset
With the rise of larger, more diverse, and ethically sourced datasets (e.g., , RFW (Racial Faces in the Wild) , and FairFace ), some researchers argue that Morph II is a historical artifact. After all, it lacks: The non-commercial version of MORPH-II (released in 2008)
The raw images in MORPH-II are non-standardized. They come in at least two different resolutions, have highly variable head poses (tilt), and exhibit inconsistent and often poor lighting conditions. Consequently, a substantial amount of pre-processing is generally required to make the images suitable for training robust machine learning models. and ethically sourced datasets (e.g.