Kyle Tomsic

Abstract

Traditional photoplethysmography (PPG) - the extraction of cardiovascular information through its modulation of light intensity- requires a device to be attached to the patient. Video PPG (vPPG) seeks to remove this requirement by observing the variations in the skin tone measurements by a webcam. While work in this field is promising, vPPG systems are sensitive to patient movement and can require long computation times for accurate results. This thesis evaluates the effect of several pre- and post-processing steps in a vPPG framework. The vPPG framework was implemented in the Python programming language with the OpenCV, NumPy, and SciPy libraries and provides homomorphic filtering, adaptive filtering, segmentation, and color space transformation capabilities. Comparison of extracted heart rates showed that, apart from color space transformation, these additional processing steps did not improve extract heart rate values. The a*channel of the L*a*b* color space was found to be significantly better than the original RGB channels for estimating heart rate.

Library of Congress Subject Headings

Heart rate monitoring--Data processing; Signal processing--Digital techniques

Publication Date

9-2014

Document Type

Thesis

Student Type

Graduate

Degree Name

Electrical Engineering (MS)

Department, Program, or Center

Electrical Engineering (KGCOE)

Advisor

Gill R. Tsouri

Advisor/Committee Member

David Borkholder

Advisor/Committee Member

Sohail A. Dianat

Comments

Physical copy available from RIT's Wallace Library at QP113 .T66 2014

Campus

RIT – Main Campus

Plan Codes

EEEE-MS

Download

Share

COinS