Abstract
Recognition of pain in patients who are incapable of expressing themselves allows for several possibilities of improved diagnosis and treatment. Despite the advancements that have already been made in this field, research is still lacking with respect to the detection of pain in live videos, especially under unfavourable conditions. To address this gap in existing research, the current study proposed a hybrid model that allowed for efficient pain recognition. The hybrid, which consisted of a combination of the Constrained Local Model (CLM), Active Appearance Model (AAM), and Patch-Based Model, was applied in conjunction with image algebra. This contributed to a system that enabled the successful detection of pain from a live stream, even with poor lighting and a low-resolution recording device. The final process and output allowed for memory for storage that was reduced up to 40%–55% and an improved processing time of 20%–25%. The experimental system met with success and was able to detect pain for the 22 analysed videos with an accuracy of 55.75%–100.00%. To increase the fidelity of the proposed technique, the hybrid model was tested on UNBC‐McMaster Shoulder Pain Database as well.
Highlights
Introduction e International Association for theStudy of Pain (IASP) defines pain as an “unpleasant sensory and emotional experience associated with actual or potential tissue damage, or described in terms of such damage” [1]
A Receiver Operating Characteristic (ROC) curve was used to exhibit the accuracy of the frame-level detection of pain in individual videos
Range was used to represent the frame-byframe accuracy percentage. is parameter was the plot of the relation between the False Acceptance Rate (FAR), which represented false positives and Hit Rates (HR), which represented true positives
Summary
Input was provided to the system in the form of a video, using formats such as .avi, .mp4, .wmv, and .mov. The extracted facial images were preprocessed, wherein they were subjected to face detection and cropping. From these images, the frame-by-frame detection and continuous tracking of specific facial feature points were carried out. Following the detection of the face in each frame, specific information known as facial feature points, facial fiducial points, or facial landmark points was extracted for further classification. Ese steps remained extremely complex in real-time implementation owing to a moving background, variations in the illumination, poses, occlusions, over fitting, local minima, and dependency on the initial shape To overcome these complexities, a hybrid model was structured, which was based on the concepts of AAM, CLM, and a Patch-Based Model. Where Vi represents the vertices that represent the parts and Ei stands for the edges that represent the connections
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
