MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641114538 A) filed by Dayananda Sagar University on September 24, 2026, for System And Method For Standardised Feature Extraction From Gas Discharge Visualization Images And Machine-Learning-Based Classification Of Physiological Stress States.
Inventors include Dr. M Shahina Parveen; Dr. Santosh Kumar J; Dr. Danthuluri Sudha; Manasvini V; Pranati Biswal; Sanmathi Y A; and Srushti S.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: A system (100) and method for classifying physiological stress from gas discharge visualization (GDV) fingertip images. A preprocessing module (104) converts each image to HSV, thresholds a corona mask, closes gaps, aligns to the mask centroid, crops and resizes. A feature extraction module (106) computes glow area, a symmetry index combining normalised left–right area and intensity differences, thickness ratio and Shannon entropy. Features are z-score normalised on training data and classified, preferably by an RBF-kernel support vector machine, into stressed or non-stressed states. Training splits original images into stratified folds before augmenting only training images, preventing data leakage. The system gives a non-invasive, interpretable stress assessment.
Disclaimer: Curated by HT Syndication.
