Deep learning analysis and age prediction from shoeprints. (October 2021)

• Record Type: Journal Article
• Authors: Hassan, Muhammad; Wang, Yan; Wang, Di; Li, Daixi; Liang, Yanchun; Zhou, You; Xu, Dong
• Is Part Of: Forensic science international. Volume 327(2021)
• Publication Date: 2021-10
• Subjects: Shoeprint -- Gait-and-standing patterns -- Aging -- Age prediction -- Deep learning -- Pressure distribution; Medical jurisprudence -- Periodicals; Chemistry, Forensic -- Periodicals; Forensic Medicine -- Periodicals; Médecine légale -- Périodiques; Chimie légale -- Périodiques; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; Chemistry, Forensic; Medical jurisprudence; Electronic journals; Periodicals; Electronic journals; 614.1
• DOI: 10.1016/j.forsciint.2021.110987
• Languages: English
• ISSNs: 0379-0738

Abstract

Highlights: This study represents the first effort to systematically explore the relationship among aging, gait pattern, and shoeprints. We have collected a large-scale annotated shoeprint dataset (100, 000 images from subjects of 7 to 80 years old). We have proposed ShoeNet model based on the comparison of different deep learning approaches to estimate age and gender. We statistically analyzed group-wise pressure distributions based on age and gender. Abstract: Human gaits are the patterns of limb movements which involve both the upper and lower body parts. These patterns in terms of step rate, gait speed, stance widening, stride, and bipedal forces are influenced by different factors including environmental (such as social, cultural, and behavioral traits) and physical changes (such as age and health status). These factors are reflected on the imprinted shoeprints generated with body forces, which in turn can be used to predict age, a problem not systematically addressed using any computational approach. We collected 100, 000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age. The model integrates various convolutional neural network models together using a skip mechanism to extract age-related features, especially in pressure and abrasion regions from pair-wise shoeprints. The results show that 40.23% of the subjects had prediction errors within 5-years of age and the prediction accuracy for gender/sex classification reached 86.07%. Interestingly, the age-related features mostly reside in the asymmetric differences between left and right shoeprints. The analysis also reveals interesting age-related and gender-related patterns in the pressure distributions on shoeprints; in particular, the pressure forces spread from the middle of the toe toward outside regions over age with gender-specific variations of forces on heel regions. Such statistics provide insight into new methods for forensic investigations, medical studies of gait pattern disorders, biometrics, and sport studies.