Application of deep learning tools in rugoscopy: Exploring digital imaging study

Abstract

Background: In forensic odontology (FO), human identification is a difficult undertaking, especially in circumstances of man-made and natural calamities. Palatal rugae, such as fingerprints and dental morphology, are highly unique, stable, and consistent throughout life. Palatoscopy or rugoscopy plays a crucial role when other methods of identification, such as fingerprints and dental records, are inaccessible. Objectives: This study aimed to understand the efficiency of deep learning in rugoscopy for human identification using digital images. Methods: Deep learning models can measure phenotypic traits, behavior, and other characteristics. This study ties together recent advances in deep learning and computer vision to meet the requirement for more efficient rugae monitoring. Sensor-based monitoring of rugae can be used in deep learning models to identify exceptionally large datasets to analyze e-information. Researchers will discuss the implementation of such solutions in rugoscopy. Results: The scope of rugoscopy prompted us with the aim to understand its efficiency in human identification using digital images.Conclusion: Computer vision and deep learning advancements may provide innovative solutions to these worldwide concerns. Observations can be effectively recorded using cameras and other sensors. Automated imaging in laboratories can also capture the physical look of specimens.

Keywords

• computer vision
• forensic odontology
• human identification