Graduate School and Research Center in Digital Sciences

Multi-spectral facial landmark detection

Keong, Jin; Dong, Xingbo; Jin, Zhe; Mallat, Khawla; Dugelay, Jean-Luc

Submitted on ArXiV, 9 June 2020

Thermal face image analysis is favorable for certain circumstances. For example, illumination-sensitive applications, like nighttime surveillance; and privacy-preserving demanded access control. However, the inadequate study on thermal face image analysis calls for attention in responding to the industry requirements. Detecting facial landmark points are important for many face analysis tasks, such as face recognition, 3D face reconstruction, and face expression recognition. In this paper, we propose a robust neural network enabled facial landmark detection, namely Deep Multi-Spectral Learning (DMSL). Briefly, DMSL consists of two sub-models, i.e. face boundary detection, and landmark coordinates detection. Such an architecture demonstrates the capability of detecting the facial landmarks on both visible and thermal images. Particularly, the proposed DMSL model is robust in facial landmark detection where the face is partially occluded, or facing different directions. The experiment conducted on Eurecom’s visible and thermal paired database shows the superior performance of DMSL over the state-of-the-art for thermal facial landmark detection. In addition to that, we have annotated a thermal face dataset with their respective facial landmark for the purpose of experimentation. 

Arxiv Bibtex

Title:Multi-spectral facial landmark detection
Department:Digital Security
Eurecom ref:6291
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted on ArXiV, 9 June 2020 and is available at :
Bibtex: @inproceedings{EURECOM+6291, year = {2020}, title = {{M}ulti-spectral facial landmark detection}, author = {{K}eong, {J}in and {D}ong, {X}ingbo and {J}in, {Z}he and {M}allat, {K}hawla and {D}ugelay, {J}ean-{L}uc}, booktitle = {{S}ubmitted on {A}r{X}i{V}, 9 {J}une 2020}, address = {}, month = {06}, url = {} }
See also: