Segmentation-Based Blood Blurring: Examining Eye-Response Differences in Gory Video Viewing

Online video platforms have enabled unprecedented access to diverse content, but minors and other vulnerable viewers can also be exposed to highly graphic or violent materials. This study addresses the need for a nuanced method of filtering gore by developing a segmentation-based approach that selectively blurs blood. We recruited 37 participants to watch both blurred and unblurred versions of five gory video clips. Eye-based physiological and gaze data, including eye openness ratio, blink frequency, and eye fixations, were recorded via a webcam and eye tracker. Our results demonstrate that partial blood blurring substantially lowers perceived gore in more brutal scenes. Additionally, participants exhibited distinctive physiological reactions when viewing clips with higher gore, such as decreased eye openness and more frequent blinking. Notably, individuals with a stronger fear of blood showed an even greater tendency to blink, suggesting that personal sensitivities shape responses to graphic content. These findings highlight the potential of segmentation-based blurring as a balanced content moderation strategy, reducing distress without fully eliminating narrative details. By allowing users to remain informed while minimizing discomfort, this approach could prove valuable for video streaming services seeking to accommodate diverse viewer preferences and safeguard vulnerable audiences.