Algorithm for predicting human age based on a convolutional neural network using only anonymized images of eye corners

Age-related biomarkers are qualitative and quantitative indicators of the human body’s aging processes. An organism’s biological age is critical in defining its physiological state. Machine learning has resulted in the development of a wide range of age predictors that differ in importance, simplicity of use, cost, applicability, and interpretability. The current work presents and investigates a noninvasive class of visual photographic markers of aging. This research describes a simple and reliable age indicator based on deep neural networks that uses just anonymised images of a person’s eye corners. In a large age range of a specific human population, the trained neural network has an average absolute error of less than three years.