Head poses and grimaces: Challenges for automated face identification algorithms?

In today's biometric and commercial settings, state-of-the-art image processing relies solely on artificial intelligence and machine learning which provides a high level of accuracy. However, these principles are deeply rooted in abstract, complex "black-box systems". When applied to forensic image identification, concerns about transparency and accountability emerge. This study explores the impact of two challenging factors in automated facial identification: facial expressions and head poses. The sample comprised 3D faces with nine prototype expressions, collected from 41 participants (13 males, 28 females) of European descent aged 19.96 to 50.89 years. Pre-processing involved converting 3D models to 2D color images (256 × 256 px). Probes included a set of 9 images per individual with head poses varying by 5° in both left-to-right (yaw) and up-and-down (pitch) directions for neutral expressions. A second set of 3,610 images per individual covered viewpoints in 5° increments from -45° to 45° for head movements and different facial expressions, forming the targets. Pair-wise comparisons using ArcFace, a state-of-the-art face identification algorithm yielded 54,615,690 dissimilarity scores. Results indicate that minor head deviations in probes have minimal impact. However, the performance diminished as targets deviated from the frontal position. Right-to-left movements were less influential than up and down, with downward pitch showing less impact than upward movements. The lowest accuracy was for upward pitch at 45°. Dissimilarity scores were consistently higher for males than for females across all studied factors. The performance particularly diverged in upward movements, starting at 15°. Among tested facial expressions, happiness and contempt performed best, while disgust exhibited the lowest AUC values.

Virtual fit and design improvements of a filtering half-mask for sub-adult wearers.

The recent pandemic has shown that protecting the general population from hazardous substances or pathogens can be a challenging and urgent task. The key element to adequate protection is appropriately sized, well-fitted and sufficiently distributed personal protective equipment (PPE). While these conditions are followed for adult PPE wearers, they are less considered when it comes to protecting subadults. In this study, the assessment of the fit and design improvements of a 3D-printed facial half mask for subadult wearers (4-18 years) is designed. The target population was represented by 1137 subadults, aged 4.06-18.94 years, for whom 3D face models were acquired. The half mask tested, which was originally provided in one subadult size, did not fit appropriately the target population. This finding prompted the creation of four size categories using the age-dependent distribution of the centroid size calculated from 7 facial landmarks. For each size category, a modified half-mask virtual design was created, including resizing and reshaping, and fit was evaluated visually and numerically using averaged and random 3D face representatives.Practitioner summary: The reason for this study was to describe procedures which led to design improvement of an existing half-mask and provide respiratory protection for subadults. To address this, fit was assessed using an innovative metric approach. Four sizes were then created based on centroid size, resulting in improved fit and design.Abbreviations: CH: cheilion landmark; CS: centroid size; EX: exocanthion landmark; GN: gnathion landmark; N: nasion landmark; PPE: personal protective equipment; PR: pronasale landmark; RPE: respiratory protective equipment.

3D human face dataset was used for modifying and validating protective equipment for subadultsTo ensure optimal protection for subadults, four size categories were proposed based on 3D face landmarks and centroid sizeModified half-mask design fit was validated virtually using a visual and numerical approach.

Normal-weight obesity frequency in the Central European urban adult female population of Brno, Czech Republic.

OBJECTIVES: The universally recognized indicator of nutritional status, BMI, has some shortcomings, especially in detecting overweight and obesity. A relatively recently introduced normal weight obesity (NWO) describes a phenomenon when individuals are found to have normal weight as indicated by BMI but have an elevated percentage of body fat. Normal weight obese individuals face a higher risk of developing metabolic syndrome, cardiometabolic dysfunction and have higher mortality. No studies have been previously performed which would map NWO in Brno, Czech Republic. METHODS: In a sample of 100 women from Brno, we assessed the percentage of normal weight obese individuals using bioelectric impedance analysis (BIA) - three different analyzers were utilized: Tanita BC-545 personal digital scale, InBody 230 and BodyStat 1500MDD. Also, a caliperation method was used to estimate body fat percentage. Various body fat percentage cut-off points were used according to different authors. RESULTS: When the 30% body fat (BF) cut-off was used, up to 14% of the women in our sample were found to be normal weight obese. When the sum of skinfolds or the 35% BF cut-off point are selected as a criterion for identifying normal weight obesity (NOW), only 1 of 100 examined women was identified as normal weight obese; at the 35% BF cut-off, BodyStat analyzer categorized no women as normal weight obese. Also, when the 30% BF or 66th percentile BF cut-off points were utilized, BodyStat identified pronouncedly fewer women from our sample to be normal-weight obese than the two other analyzers. CONCLUSIONS: On a pilot sample of Czech women, we demonstrated that depending on the selected cut-off (there is no clear agreement on cut-off points in literature), up to 14% of the examined women were found to be normal weight obese.