Evaluation of facial landmark localization performance in a surgical setting

TL;DR

This study evaluates the MediaPipe facial landmark detection algorithm in a surgical setting, demonstrating improved accuracy under surgical lighting and discussing its potential integration into medical procedures.

Contribution

It provides an experimental assessment of MediaPipe's performance in surgical lighting conditions, highlighting its robustness and potential clinical applications.

Findings

Improved detection accuracy under surgical lighting.

Enhanced performance at larger yaw and pitch angles.

Identified variability in landmark detection precision.

Abstract

The use of robotics, computer vision, and their applications is becoming increasingly widespread in various fields, including medicine. Many face detection algorithms have found applications in neurosurgery, ophthalmology, and plastic surgery. A common challenge in using these algorithms is variable lighting conditions and the flexibility of detection positions to identify and precisely localize patients. The proposed experiment tests the MediaPipe algorithm for detecting facial landmarks in a controlled setting, using a robotic arm that automatically adjusts positions while the surgical light and the phantom remain in a fixed position. The results of this study demonstrate that the improved accuracy of facial landmark detection under surgical lighting significantly enhances the detection performance at larger yaw and pitch angles. The increase in standard deviation/dispersion occurs due to imprecise detection of selected facial landmarks. This analysis allows for a discussion on the potential integration of the MediaPipe algorithm into medical procedures.