Date of Graduation
5-2019
Document Type
Thesis
Degree Name
Bachelor of Science
Degree Level
Undergraduate
Department
Computer Science and Computer Engineering
Advisor/Mentor
Li Ph.D., Qinghua
Committee Member/Reader
Gauch Ph.D., John
Committee Member/Second Reader
Thompson Ph.D., Dale
Abstract
The purpose of this thesis is to analyze the usage of multiple image blurring techniques and determine their effectiveness in combatting facial detection algorithms. This type of analysis is anticipated to reveal potential flaws in the privacy expected from blurring images or, rather, portions of images. Three different blurring algorithms were designed and implemented: a box blurring method, a Gaussian blurring method, and a differential privacy-based pixilation method. Datasets of images were collected from multiple sources, including the AT&T Database of Faces. Each of these three methods were implemented via their own original method, but, because of how common they are, box blurring and Gaussian blurring were also implemented utilizing the OpenCV open-source library to conserve time. Extensive tests were run on each of these algorithms, including how the blurring acts on color and grayscale images, images with and without faces, and the effectiveness of each blurring algorithm in hiding faces from being detected via the popular open-source OpenCV library facial detection method. Of the chosen blurring techniques, the differential privacy blurring method appeared the most effective against mitigating facial detection.
Keywords
image, processing, blurring, privacy, security, facial
Citation
Pulfer, E. (2019). Different Approaches to Blurring Digital Images and Their Effect on Facial Detection. Computer Science and Computer Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/csceuht/66