Translator Disclaimer
1 October 2018 Tuning deep learning algorithms for face alignment and pose estimation
Author Affiliations +
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
Back to Top