首页|University Hospital Augsburg Reports Findings in Artificial Intelligence (Differ ences in the annotation between facial images and videos for training an artific ial intelligence for skin type determination)
University Hospital Augsburg Reports Findings in Artificial Intelligence (Differ ences in the annotation between facial images and videos for training an artific ial intelligence for skin type determination)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report.According to news originating from Augsburg,Germa ny,by NewsRx correspondents,research stated,"The Grand- AID research project,consisting of GRANDEL-The Beautyness Company,the dermatology department of Augs burg University Hospital and the Chair of IT Infrastructure for Translational Me dical Research at Augsburg University,is currently researching the development of a digital skin consultation tool that uses artificial intelligence (AI) to an alyze the user's skin and ultimately perform a personalized skin analysis and a customized skin care routine.Training the AI requires annotation of various ski n features on facial images." Our news journalists obtained a quote from the research from University Hospital Augsburg,"The central question is whether videos are better suited than static images for assessing dynamic parameters such as wrinkles and elasticity.For th is purpose,a pilot study was carried out in which the annotations on images and videos were compared.Standardized image sequences as well as a video with faci al expressions were taken from 25 healthy volunteers.Four raters with dermatolo gical expertise annotated eight features (wrinkles,redness,shine,pores,pigme ntation spots,dark circles,skin sagging,and blemished skin) with a semi-quant itative and a linear scale in a cross-over design to evaluate differences betwee n the image modalities and between the raters.In the videos,most parameters te nded to be assessed with higher scores than in the images,and in some cases sig nificantly.Furthermore,there were significant differences between the raters.The present study shows significant differences between the two evaluation metho ds using image or video analysis.In addition,the evaluation of the skin analys is depends on subjective criteria."
AugsburgGermanyEuropeArtificial In telligenceEmerging TechnologiesMachine Learning
NETL
NSTL
