Investigating the Effect of Material and Shape Abstraction on Object Recognition for Private Objects in Augmented Reality Environments

Shared Augmented Environments (AEs) introduce both opportunities and challenges in terms shared content and privacy. We present three abstraction techniques to balance privacy and context in collaborative Augmented Reality (AR) applications. We developed three abstraction techniques, polygon count reduction (PCR), blurring, and blurred PCR (BPCR). We conducted a study aimed to evaluate the effects of these techniques on object recognition in AR. Results indicate that altering shape and material significantly impacts the certainty and ability of object recognition, with variations observed across different object types. The implications of this research extend to the design and implementation of privacy-aware collaborative AR applications, emphasising the need to strike a balance between providing context and respecting user privacy.