Development of a video data tagger via audio fingerprinting and watermarking

• Main Author: Lau, Gerald Ngai Jun
• Other Authors: Owen Noel Newton Fernando
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Computer science and engineering::Computer applications::Computer-aided engineering
• Online Access: https://hdl.handle.net/10356/138034
• Institution: Nanyang Technological University

The Video Data Tagger is an application that allows users to embed links in to the audio tracks of videos. It can then be used to later retrieve previously embedded links from videos, and display them. The two users are Uploaders and General Users. Uploaders will be able to upload videos and embed links into them using two modes, Audio Watermarking and Audio Fingerprinting. They will also be able to manage their accounts and see past uploaded videos. General users will be able to use the application to retrieve embedded links, using their device microphone. The Video Data Tagger is served as a Single Page Web Application (SPA), and is developed using Vue.JS, Flask and MongoDB. It is deployed on a NTU Virtual Computer, and can be accessed by users who are on the NTU network or VPN. This report details the development of the Video Data Tagger, and also compares the accuracy of the two modes available. It then draws conclusions on the suitability of each mode for different scenarios.