TY - JOUR AU - Chwyl, Brendan AU - Amelard, Robert AU - Clausi, David AU - Wong, Alexander PY - 2016/10/03 Y2 - 2024/03/29 TI - A Bayesian Multi-Scale Framework for Photoplethysmogram Imaging Waveform Processing JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 2 IS - 1 SE - Articles DO - 10.15353/vsnl.v2i1.114 UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/114 SP - AB - <p>Photoplethysmography imaging (PPGI) is an increasingly popular<br />technique for remotely creating signals with a plethora of medical<br />information, referred to as PPGI waveforms. However, PPGI waveforms<br />are often heavily affected by illumination variation and motion<br />artefacts. Current PPGI waveform processing methods are useful<br />for estimating heart rate, however, structural detail is not preserved,<br />rendering the signal incapable of providing additional medical information.<br />For this reason, we propose a multi-scale framework based<br />on the Bayesian residual transform which aims to suppress noise<br />and preserve structural details necessary for extracting cardiovascular<br />information beyond the scope of heart rate. Experiments conducted<br />on a dataset consisting of 24 different PPGI waveforms and<br />corresponding PPG waveforms captured via a finger pulse oximeter<br />suggests a high level of noise and ambient illumination variation<br />suppression is achieved while signal fidelity is largely retained.</p> ER -