Enhanced face alignment using an unsupervised roll estimation initialization

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

We propose a novel and efficient initialization method for generalized facial landmark localization with an unsupervised roll-angle estimation based on B-spline models. We first show that the roll angle is crucial for an accurate landmark localization. Therefore, we develop an unsupervised roll-angle estimation by adopting a joint 1 st -order B-spline model, which is robust to intensity variations and generic for application to various face detectors. The method consists of three steps. First, the scaled-normalized Laplacian of Gaussian operator is applied to a bounding box generated by a face detector for extracting facial feature segments. Second, a joint 1 st -order B-spline model is fitted to the extracted facial feature segments, using an iterative optimization method. Finally, the roll angle is estimated through the aligned segments. We evaluate four state-of-the-art landmark localization schemes with the proposed roll-angle estimation initialization in the benchmark dataset. The proposed method boosts the performance of landmark localization in general, especially for cases with large head pose. Moreover, the proposed unsupervised roll-angle estimation method outperforms the standard supervised methods, such as random forest and support vector regression by 41.6% and 47.2%, respectively.

Original languageEnglish
Title of host publicationEleventh International Conference on Machine Vision, ICMV 2018
EditorsJianhong Zhou, Petia Radeva, Dmitry P. Nikolaev, Antanas Verikas
Place of PublicationBellingham
PublisherSPIE
Number of pages9
ISBN (Electronic)9781510627482
DOIs
Publication statusPublished - 15 Mar 2019
Event11th International Conference on Machine Vision, ICMV 2018 - Munich, Germany
Duration: 1 Nov 20183 Nov 2018
Conference number: 11

Publication series

NameProceedings of SPIE
Volume11041

Conference

Conference11th International Conference on Machine Vision, ICMV 2018
Abbreviated titleICMV
CountryGermany
CityMunich
Period1/11/183/11/18

Keywords

  • B-spline model
  • landmark localization
  • unsupervised roll-angle estimation

Fingerprint Dive into the research topics of 'Enhanced face alignment using an unsupervised roll estimation initialization'. Together they form a unique fingerprint.

  • Cite this

    Li, C., Pourtaherian, A., Tjon A Ten, W. E., & de With, P. H. N. (2019). Enhanced face alignment using an unsupervised roll estimation initialization. In J. Zhou, P. Radeva, D. P. Nikolaev, & A. Verikas (Eds.), Eleventh International Conference on Machine Vision, ICMV 2018 [110412C] (Proceedings of SPIE; Vol. 11041). SPIE. https://doi.org/10.1117/12.2523111