University of Twente Student Theses

Login

Automatic detection of photographing or filming

Chen, Zhiyuan (2020) Automatic detection of photographing or filming.

[img] PDF
6MB
Abstract:A wide use of cameras and portable devices with built in cameras such as smartphones and social media makes taking photos and sharing very easy, while unintentional capture of facial image brings privacy concerns. To detect photographing or filming, a detection model using the state of the art architecture of Faster R CNN is designed to detect camera objects on still images, which lays a foundation of the work of real time detection of photographing or filming. Choices such as selection of feature extractors, dataset selection and number of region proposals are made on different models. Each model is tested and evaluated concerning performance, false negative rate and bounding boxes etc.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:50 technical science in general, 54 computer science
Programme:Creative Technology BSc (50447)
Link to this item:http://purl.utwente.nl/essays/82513
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page