Naslov
Towards Neural Art-based Face De-identification in Video Data

Autori
Brkić, Karla ; Hrkać, Tomislav ; Sikirić, Ivan ; Kalafatić, Zoran

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016 First International Workshop on / - Aaalborg : Institute of Electrical and Electronics Engineers (IEEE), 2016, 11-15

ISBN
978-1-4673-8917-4

Skup
First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE)

Mjesto i datum
Aalborg, Danska, 06.07.2016. - 08.07.2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
deep learning; neural art; face de-identification

Sažetak
We propose a computer vision-based pipeline that enables altering the appearance of faces in videos. Assuming a surveillance scenario, we combine GMM-based background subtraction with an improved version of the GrabCut algorithm to find and segment pedestrians. Independently, we detect faces using a standard face detector. We apply the neural art algorithm, utilizing the responses of a deep neural network to obfuscate the detected faces through style mixing with reference images. The altered faces are combined with the original frames using the extracted pedestrian silhouettes as a guideline. Experimental evaluation indicates that our method has potential in producing de-identified versions of the input frames while preserving the utility of the de-identified data.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA