Date of Graduation
2015
Document Type
Thesis
Degree Type
MS
College
Statler College of Engineering and Mineral Resources
Department
Lane Department of Computer Science and Electrical Engineering
Committee Chair
Roy S Nutter
Committee Co-Chair
Donald A Adjeroh
Committee Member
Thirimachos Bourlai
Abstract
This work quantitatively measures the impact of modifying the nasal width and length dimensions, in a simulated plastic surgery, on the Facial Recognition algorithms, Principal Component Analysis (PCA), Linear Discrimination Analysis (LDA), and Local Binary Patterns Histogram (LBPH). This was integrated through the use of OpenCV. It was found that as the nose width increases beyond 40% its original width, there is an average decrease in facial recognition performance of up to 14%. It was also found that as the nose was modified vertically, there was less than a 3% decrease in performance for the facial recognition algorithms. These rates are consistent with previous research in the field although, these are more quantitative. The experimental structure used is modular in nature and allows for easy insertion of other Facial Recognition Algorithms and other Facial Recognition Datasets.
Recommended Citation
Wolen, Jacob, "Impact assessment of facial recognition algorithms' performance when modifying nose dimensions" (2015). Graduate Theses, Dissertations, and Problem Reports. 6967.
https://researchrepository.wvu.edu/etd/6967