Premium
Implementation of facial recognition with Microsoft Kinect v2 sensor for patient verification
Author(s) -
Silverstein Evan,
Snyder Michael
Publication year - 2017
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.12241
Subject(s) - computer science , artificial intelligence , computer vision , fiducial marker , facial recognition system , matching (statistics) , identification (biology) , process (computing) , set (abstract data type) , data set , pattern recognition (psychology) , sensitivity (control systems) , blossom algorithm , template matching , mathematics , image (mathematics) , engineering , statistics , botany , biology , programming language , operating system , electronic engineering
Purpose The aim of this study was to present a straightforward implementation of facial recognition using the Microsoft Kinect v2 sensor for patient identification in a radiotherapy setting. Materials and methods A facial recognition system was created with the Microsoft Kinect v2 using a facial mapping library distributed with the Kinect v2 SDK as a basis for the algorithm. The system extracts 31 fiducial points representing various facial landmarks which are used in both the creation of a reference data set and subsequent evaluations of real‐time sensor data in the matching algorithm. To test the algorithm, a database of 39 faces was created, each with 465 vectors derived from the fiducial points, and a one‐to‐one matching procedure was performed to obtain sensitivity and specificity data of the facial identification system. ROC curves were plotted to display system performance and identify thresholds for match determination. In addition, system performance as a function of ambient light intensity was tested. Results Using optimized parameters in the matching algorithm, the sensitivity of the system for 5299 trials was 96.5% and the specificity was 96.7%. The results indicate a fairly robust methodology for verifying, in real‐time, a specific face through comparison from a precollected reference data set. In its current implementation, the process of data collection for each face and subsequent matching session averaged approximately 30 s, which may be too onerous to provide a realistic supplement to patient identification in a clinical setting. Despite the time commitment, the data collection process was well tolerated by all participants and most robust when consistent ambient light conditions were maintained across both the reference recording session and subsequent real‐time identification sessions. Conclusion A facial recognition system can be implemented for patient identification using the Microsoft Kinect v2 sensor and the distributed SDK . In its present form, the system is accurate—if time consuming—and further iterations of the method could provide a robust, easy to implement, and cost‐effective supplement to traditional patient identification methods.