The impact of privacy protection filters on gender recognition

Deep learning-based algorithms have become increasingly efficient in recognition and detection tasks, especially when they are trained on large-scale datasets. Such recent success has led to a speculation that deep learning methods are comparable to or even outperform human visual system in its ability to detect and recognize objects and their features. In this paper, we focus on the specific task of gender recognition in images when they have been processed by privacy protection filters (e.g., blurring, masking, and pixelization) applied at different strengths. Assuming a privacy protection scenario, we compare the performance of state of the art deep learning algorithms with a subjective evaluation obtained via crowdsourcing to understand how privacy protection filters affect both machine and human vision.

Published in:
Applications of Digital Image Processing XXXVIII, 959906
Presented at:
SPIE Optical Engineering + Applications, San Diego, California, USA, August 10-13, 2015

 Record created 2015-08-27, last modified 2018-01-28

External link:
Download fulltext
Publisher's version
Rate this document:

Rate this document:
(Not yet reviewed)