Living-skin classification via remote-PPG

Research output: Contribution to journalArticleAcademicpeer-review

23 Citations (Scopus)
1 Downloads (Pure)

Abstract

Detecting living-skin tissue in a video on the basis of induced color changes due to blood pulsation is emerging for automatic region of interest localization in remote photoplethysmography (rPPG). However, the state-of-the-art method performing unsupervised living-skin detection in a video is rather time-consuming, which is mainly due to the high complexity of its unsupervised on-line learning for pulse/noise separation. In this paper, we address this issue by proposing a fast living-skin classification method. Our basic idea is to transform the time-variant rPPG-signals into signal shape descriptors called “Multi-resolution Iterative Spectrum” (MIS), where pulse and noise have different patterns enabling accurate binary classification. The proposed technique is a proof-of-concept that has only been validated in lab conditions but not in real clinical conditions. The benchmark, including synthetic and realistic (non-clinical) experiments, shows that it achieves a high detection accuracy better than the state-of-the-art method, and a high detection speed at hundreds of frames per second in Matlab, enabling real-time living-skin detection.
Original languageEnglish
Article number7867752
Pages (from-to)2781-2792
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
Volume64
Issue number12
DOIs
Publication statusPublished - Dec 2017

Keywords

  • Biomedical monitoring
  • Remote sensing
  • Photoplethysmography
  • Supervised learning
  • Face detection
  • photoplethysmography
  • face detection
  • supervised learning
  • remote sensing
  • Biometric Identification/methods
  • Humans
  • Photoplethysmography/methods
  • Male
  • Skin/diagnostic imaging
  • Algorithms
  • Image Processing, Computer-Assisted/methods
  • Signal Processing, Computer-Assisted
  • Female

Fingerprint

Dive into the research topics of 'Living-skin classification via remote-PPG'. Together they form a unique fingerprint.

Cite this