Subject: De-identification
Subject: Nonfrontal face detection
Subject: Pose estimation
Subject: Classifier fusion
Subject: SVM
Subject: Logistic regression
Year: 2016
Type: Book chapter
Title: Generic Face Detection and Pose Estimation Algorithm Suitable for the Face De-identification Problem
Author: Milchevski, Aleksandar
Author: Petrovska-Delacrétaz, Dijana
Author: GJorgjevikj, Dejan
Abstract: In this work we tackle the problem of face de-identification in an image. The first step towards a solution to this problem is the design of a successful generic face detection algorithm, which will detect all of the faces in the image or video, regardless of the pose. If the face detection algorithm fails to detect even one face, the effect of the de-identification algorithm could be neutralized. That is why a novel face detection algorithm is proposed for face detection and pose estimation. The algorithm uses an ensemble of three linear SVM classifiers. The first, second and the third SVM classifier estimate the pitch, yaw and roll angle of the face and a logistic regression is used to combine the results and output a final decision. Second, the results of the face detection and a simple space variant de-identification algorithm are used to show the benefits of simultaneous face detection and face de-identification.
Publisher: SpringerNature
Relation: Advances in Intelligent Systems and Computing
Identifier: oai:repository.ukim.mk:20.500.12188/17141
Identifier: Milchevski, A., Petrovska-Delacrétaz, D., Gjorgjevikj, D. (2016). Generic Face Detection and Pose Estimation Algorithm Suitable for the Face De-identification Problem. In: Loshkovska, S., Koceski, S. (eds) ICT Innovations 2015 . ICT Innovations 2015. Advances in Intelligent Systems and Computing, vol 399. Springer, Cham. https://doi.org/10.1007/978-3-319-25733-4_23Identifier: 978-3-319-25733-4
Identifier: http://hdl.handle.net/20.500.12188/17141Identifier: 10.1007/978-3-319-25733-4_23
Identifier: 399
Identifier: 225
Identifier: 234
