University of Twente Student Theses


Implementation and optimization of facial recognition with the IntelRealsense SR300

Delaere, Yvo (2017) Implementation and optimization of facial recognition with the IntelRealsense SR300.

[img] PDF
Abstract:This article describes the continuation and improvement of a method for using facial recognition together with the Intel Realsense SR300 camera. The previous work described that reliable facial recognition can be obtained within the correct environment and the correct settings at a range from 25- up to 40 centimeter. An application framework is described and built to create a user friendly environment for the facial recognition and makes the previous method more accessible to the public. With some modifications, it can be used with any 3D image acquisition device. Furthermore, improvements are suggested and implemented to improve the quality and range of the facial recognition. An attempt has been made to make a reliable facial recognition system at between the user and camera of 60 centimeter. A small sample size of 6 persons has been used to examine the quality. Although all persons are recognized correctly, the expectation is that with a larger sample size false validations will occur, due to poor registered images as a result of shortcoming of the camera.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:53 electrotechnology, 54 computer science
Programme:Electrical Engineering BSc (56953)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page