2019/03/26 by Jizhe Zhou, Zhou, Jizhe, Chi-Man Pun +5
Computer Science · #Advanced Image and Video Retrieval Techniques #Face recognition and analysis #Video Surveillance and Tracking Methods #cs.CR #cs.CV
paper · pdf · doi:10.48550/arxiv.1903.10836
major modification on GP models
arxiv created 2019/04/24 · arxiv updated 2019/04/25
This paper introduces an algorithm to protect the privacy of individuals in streaming video data by blurring faces such that face cannot be reliably recognized. This thwarts any possible face recognition, but because all facial details are obscured, the result is of limited use. We propose a new clustering algorithm to create raw trajectories for detected faces. Associating faces across frames to form trajectories, it auto-generates cluster number and discovers new clusters through deep feature and position aggregated affinities. We introduce a Gaussian Process to refine the raw trajectories. We conducted an online experiment with 47 participants to evaluate the effectiveness of face blurring compared to the original photo (as-is), and users' experience (satisfaction, information sufficiency, enjoyment, social presence, and filter likeability)