RESUMO
Knowledge of a person's level of skin pigmentation, or so-called "skin tone", has proven to be an important building block in improving the performance and fairness of various applications that rely on computer vision. These include medical diagnosis of skin conditions, cosmetic and skincare support, and face recognition, especially for darker skin tones. However, the perception of skin tone, whether by the human eye or by an optoelectronic sensor, uses the reflection of light from the skin. The source of this light, or illumination, affects the skin tone that is perceived. This study aims to refine and assess a convolutional neural network-based skin tone estimation model that provides consistent accuracy across different skin tones under various lighting conditions. The 10-point Monk Skin Tone Scale was used to represent the skin tone spectrum. A dataset of 21,375 images was captured from volunteers across the pigmentation spectrum. Experimental results show that a regression model outperforms other models, with an estimated-to-target distance of 0.5. Using a threshold estimated-to-target skin tone distance of 2 for all lights results in average accuracy values of 85.45% and 97.16%. With the Monk Skin Tone Scale segmented into three groups, the lighter exhibits strong accuracy, the middle displays lower accuracy, and the dark falls between the two. The overall skin tone estimation achieves average error distances in the LAB space of 16.40±20.62.
RESUMO
Face recognition is widely used for security and access control. Its performance is limited when working with highly pigmented skin tones due to training bias caused by the under-representation of darker-skinned individuals in existing datasets and the fact that darker skin absorbs more light and therefore reflects less discernible detail in the visible spectrum. To improve performance, this work incorporated the infrared (IR) spectrum, which is perceived by electronic sensors. We augmented existing datasets with images of highly pigmented individuals captured using the visible, IR, and full spectra and fine-tuned existing face recognition systems to compare the performance of these three. We found a marked improvement in accuracy and AUC values of the receiver operating characteristic (ROC) curves when including the IR spectrum, increasing performance from 97.5% to 99.0% for highly pigmented faces. Different facial orientations and narrow cropping also improved performance, and the nose region was the most important feature for recognition.
RESUMO
Fundamental ecological principles of ecosystem-level respiration are extensively applied in greenhouse gas and elemental cycle studies. A laboratory system termed CEMS (Carbon Dioxide Evolution Measurement System), developed to explore microbial biofilm growth and metabolic responses, was evaluated as an early-warning system for microbial disturbances in industrial settings: in (a) potable water system contamination, and (b) bioreactor inhibition. Respiration was detected as CO2 production, rather than O2 consumption, including aerobic and anaerobic metabolism. Design, thresholds, and benefits of the remote CO2 monitoring technology were described. Headspace CO2 correlated with contamination levels, as well as chemical (R2 > 0.83-0.96) and microbiological water quality indicators (R2 > 0.78-0.88). Detection thresholds were limiting factors in monitoring drinking water to national and international standards (0 CFU/100 mL fecal coliforms) in both open- (>1500 CFU/mL) and closed-loop CO2 measuring regimes (>100 CFU/100 mL). However, closed-loop detection thresholds allow for the detection of significant contamination events, and monitoring less stringent systems such as irrigation water (<100 CFU/mL). Whole-system respiration was effectively harnessed as an early-warning system in bioreactor performance monitoring. Models were used to deconvolute biological CO2 fluctuations from chemical CO2 dynamics, to optimize this real-time, sustainable, low-waste technology, facilitating timeous responses to biological disturbances in bioreactors.
