Tuning deep learning algorithms for face alignment and pose estimation

Rafal Pilarczyk; Władysław Skarbek

doi:10.1117/12.2501682

1 October 2018 Tuning deep learning algorithms for face alignment and pose estimation

Rafal Pilarczyk, Władysław Skarbek

Proceedings Volume 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018; 108081A (2018) https://doi.org/10.1117/12.2501682
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 2018, Wilga, Poland

Abstract

In this paper tuning for deep learning algorithms is performed for face alignment and pose estimation problems. For pose estimation the classical indirect method (from fp68 landmarks via Candide model to pose) is compared with direct method when both the landmarks and the pose are obtained by regressive deep neural network (DNN) algorithms of VGG type. Indirect method appeared slightly more accurate than the direct one with respect to inter-ocular, inter-pupil, and box-diagonal measures . We analyzed also both indirect and direct DNN algorithms in two scenarios of resolution reducing for convoluted data tensors: via max-pooling and via striding of convolution operations. The striding algorithms exhibit relatively low amount of parameters (around 10 percent of max-pooling version compression) traded for slight loss of accuracy.

Citation Download Citation

Rafal Pilarczyk and Władysław Skarbek "Tuning deep learning algorithms for face alignment and pose estimation", Proc. SPIE 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 108081A (1 October 2018); https://doi.org/10.1117/12.2501682

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available