ViDupe-Duplicate Video Detection as a Service in Cloud

Detecting near-duplicate videos in the cloud is computationally intensive due to sheer number of videos and their large file sizes. To address this challenge, we propose to improve algorithm efficiency by enhancing and revising existing metadata and content comparison methods, and to enable public access by developing a web service. As a proof of concept, a duplicate video detection system called ViDupe is developed that can quickly scans user’s Google drive for duplicates.

[1]  Sudeep D. Thepade,et al.  An optimized key frame extraction for detection of near duplicates in content based video retrieval , 2014, 2014 International Conference on Communication and Signal Processing.

[2]  Vishal Monga,et al.  Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs , 2006, IEEE Transactions on Image Processing.

[3]  Chong-Wah Ngo,et al.  Practical elimination of near-duplicates from web video search , 2007, ACM Multimedia.

[4]  Zi Huang,et al.  UQLIPS: A Real-time Near-duplicate Video Clip Detection System , 2007, VLDB.

[5]  Junsong Yuan,et al.  From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Henrique S. Malvar,et al.  Using audio fingerprinting for duplicate detection and thumbnail generation , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[7]  Yilong Yin,et al.  Two-layer video fingerprinting strategy for near-duplicate video detection , 2017, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).