Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination.

BACKGROUND: The Grand-AID research project, consisting of GRANDEL-The Beautyness Company, the dermatology department of Augsburg University Hospital and the Chair of IT Infrastructure for Translational Medical Research at Augsburg University, is currently researching the development of a digital skin consultation tool that uses artificial intelligence (AI) to analyze the user's skin and ultimately perform a personalized skin analysis and a customized skin care routine. Training the AI requires annotation of various skin features on facial images. The central question is whether videos are better suited than static images for assessing dynamic parameters such as wrinkles and elasticity. For this purpose, a pilot study was carried out in which the annotations on images and videos were compared. MATERIALS AND METHODS: Standardized image sequences as well as a video with facial expressions were taken from 25 healthy volunteers. Four raters with dermatological expertise annotated eight features (wrinkles, redness, shine, pores, pigmentation spots, dark circles, skin sagging, and blemished skin) with a semi-quantitative and a linear scale in a cross-over design to evaluate differences between the image modalities and between the raters. RESULTS: In the videos, most parameters tended to be assessed with higher scores than in the images, and in some cases significantly. Furthermore, there were significant differences between the raters. CONCLUSION: The present study shows significant differences between the two evaluation methods using image or video analysis. In addition, the evaluation of the skin analysis depends on subjective criteria. Therefore, when training the AI, we recommend regular training of the annotating individuals and cross-validation of the annotation.

Are target-shooters more aggressive than the general population?

Although psychological research shows that guns are aggressive cues, proponents of liberal gun control argue that people rather than guns are to blame for gun-related violence. For instance, athletic target-shooters might classify guns as athletic rather than aggressive stimuli and thus should not be more aggressive than the general population. The present work investigated aggression and emotion-regulation in target-shooters. A longitudinal study found that initial self-reported aggression in target-shooters was higher than in the general population and further increased over 1 year. Additionally, the sample exhibited deficient emotion-regulation strategies, and this was related to self-reported aggression. In contrast, their implicit self-construct became more peaceful over time but was unrelated to all other measures. Two further cross-sectional experiments explored the causal impact of athletic target-shooting and other athletic activities (shooting a basketball) on aggression. Target-shooters and basketball players were tested before and after their regular team practice and aggressive thoughts and feelings were measured. Target-shooting but not basketball practice activated aggressive and anxiety-related thought more strongly than positive thought. Future research avenues, implications for the indirect measurement of aggression, and possible interventions to decrease aggression in target-shooters are discussed. Aggr. Behav. 43:3-13, 2017. © 2016 Wiley Periodicals, Inc.