000210824 001__ 210824
000210824 005__ 20190416055548.0
000210824 0247_ $$2doi$$a10.1117/12.2193647
000210824 02470 $$2ISI$$a000366385200005
000210824 037__ $$aCONF
000210824 245__ $$aThe impact of privacy protection filters on gender recognition
000210824 269__ $$a2015
000210824 260__ $$c2015
000210824 336__ $$aConference Papers
000210824 490__ $$aProceedings of SPIE$$v9599
000210824 520__ $$aDeep 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.
000210824 6531_ $$aGender Recognition
000210824 6531_ $$aDeep Learning
000210824 6531_ $$aCrowdsourcing
000210824 700__ $$aRuchaud, Natacha
000210824 700__ $$aAntipov, Grigory
000210824 700__ $$aKorshunov, Pavel
000210824 700__ $$aDugelay, Jean-Luc
000210824 700__ $$0240223$$g105043$$aEbrahimi, Touradj
000210824 700__ $$aBerrani, Sid-Ahmed
000210824 7112_ $$dAugust 10-13, 2015$$cSan Diego, California, USA$$aSPIE Optical Engineering + Applications
000210824 773__ $$tApplications of Digital Image Processing XXXVIII$$q959906
000210824 8564_ $$uhttps://infoscience.epfl.ch/record/210824/files/spie-2015-gender-recognition.pdf$$zPublisher's version$$s521518$$yPublisher's version
000210824 909C0 $$0252077$$pMMSPL
000210824 909CO $$pSTI$$ooai:infoscience.tind.io:210824$$qGLOBAL_SET$$pconf
000210824 917Z8 $$x212659
000210824 917Z8 $$x148230
000210824 937__ $$aEPFL-CONF-210824
000210824 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000210824 980__ $$aCONF