A Robust Framework for Heart Rate Estimation from Facial Video Signals Using Signal Enhancement Techniques

Krishi Verma; Arya Sharma; Bhawna Sharma; Sheetal Gandotra

doi:10.36948/ijfmr.2025.v07i04.48696

A Robust Framework for Heart Rate Estimation from Facial Video Signals Using Signal Enhancement Techniques

Author(s)	Mr. Krishi Verma, Ms. Arya Sharma, Prof. Dr. Bhawna Sharma, Ms. Sheetal Gandotra
Country	India
Abstract	The demand for non-contact, unobtrusive methods of physiological monitoring has grown significantly with the expansion of telehealth and remote diagnostics. This paper presents a novel technique for estimating heart rate using standard RGB facial video, eliminating the need for wearable sensors or traditional photoplethysmography. The method leverages variations in pixel intensity across selected facial regions—specifically the forehead and cheeks—to extract temporal signals that reflect subtle skin tone changes caused by blood flow. The captured signals undergo a series of preprocessing steps, including normalisation and bandpass filtering, to isolate physiological frequency components typically associated with cardiac activity. To analyse these non-stationary signals with high precision, a custom implementation of the Superlet Transform is employed. This transform enhances time-frequency resolution by combining multiple wavelets of varying orders, yielding a superresolved spectrogram. Following this, Welch’s Power Spectral Density (PSD) is applied to determine the dominant frequency within the physiological range, which is then converted to beats per minute (BPM). The system was evaluated on videos recorded at 30 frames per second and demonstrated reliable heart rate estimation across all tested facial regions. Results showed consistent peak detection in the PSD and clear frequency concentration in the Superlet spectrograms, confirming the method’s accuracy and robustness. This approach offers a promising direction for real-time, camera-based vital sign monitoring in clinical, fitness, and consumer applications, especially where sensor-based approaches are impractical. It also opens avenues for further research in enhancing signal quality under motion, lighting variation, and across diverse skin tones.
Keywords	Heart rate estimation, video-based monitoring, Superlet Transform, time-frequency analysis, facial signal processing, noncontact vital signs, Welch PSD, signal preprocessing, pixel intensity variation, camera-based health monitoring.
Field	Engineering
Published In	Volume 7, Issue 4, July-August 2025
Published On	2025-07-05
DOI	https://doi.org/10.36948/ijfmr.2025.v07i04.48696
Short DOI	https://doi.org/g9s88v

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 4 Cover Page Vol 7 Isu 3 Cover Page Vol 7 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Robust Framework for Heart Rate Estimation from Facial Video Signals Using Signal Enhancement Techniques

Share this