Skin Segmentation for Imaging Photoplethysmography Using a Specialized Deep Learning Approach

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review



Imaging photoplethysmography (iPPG) is a camera-based approach for the remote measurement of superficial tissue perfusion most commonly applied to facial video recordings. Since only tissue contains information about perfusion, skin detection is a necessary processing step. Several approaches for the detection of skin pixels in video recordings have been developed, e.g. using color thresholds. Within this work we present a deep learning based approach capable of combining color and morphology information, which makes the skin detection robust against different illumination conditions. We evaluated our new approach using two datasets with 182 individuals of different gender, age, skin tone and illumination conditions. Our approach outperformed state-of-the-art algorithms or yielded at least comparable results (mean absolute error of estimated pulse rate improved by up to 68 %). The method presented allows more accurate assessment of superficial tissue perfusion with iPPG.


Original languageEnglish
Title of host publication48th Conference Computing in Cardiology (CinC)
PublisherWiley-IEEE Press
Number of pages4
ISBN (print)978-1-6654-6721-6
Publication statusPublished - 15 Sept 2021


Title2021 Computing in Cardiology (CinC)
Abbreviated titleCinC 2021
Conference number48
Duration12 - 15 September 2021
Degree of recognitionInternational event
LocationHotel Passage & online
CountryCzech Republic

External IDs

Scopus 85124729976
ORCID /0000-0001-6754-5257/work/142232820
ORCID /0000-0003-4012-0608/work/142235698


Sustainable Development Goals


  • Deep learning, Image color analysis, Statistical analysis, Neural networks, Lighting, Imaging, Photoplethysmography