A Robust Zero-Watermark Scheme with Similarity-based Retrieval for Copyright Protection of 3D Video

by   Xiyao Liu, et al.

The copyright protection of 3D videos has become a crucial issue. In this study, a novel zero-watermark scheme with similarity-based retrieval is proposed. In our proposed scheme the features of both 2D-video and depth-map components are first extracted. Next, master shares and ownership shares are generated from these features and their relevant copyright information based on (2,2) visual secret sharing scheme. Different with traditional zero-watermark schemes, both the features and ownership shares are stored in relevant databases. When a 3D video is queried, a novel similarity-based retrieval phase is designed to obtain the ownership shares relevant to the particular 3D video. After that, the queried master shares are generated from this 3D video and stacked with its relevant ownership shares to identify its copyright ownership. To satisfy different DRM requirements of 3D videos, flexible mechanisms are designed for both similarity-based retrieval and copyright identification functions in our study. The experimental results demonstrate that RZW-SR3D not only obtains the ownership shares relevant to a particular 3D video precisely and reliably when processing numerous videos, which outperforms the traditional zero-watermark schemes, but also identifies the copyrights of 2D-video and depth-map components of 3D videos reliably, independently and simultaneously without any content distortion or watermark-embedding limitation, which outperforms existing 2D-video based and depth-map based watermark schemes for protecting 3D video.


page 7

page 10


On Semantic Similarity in Video Retrieval

Current video retrieval efforts all found their evaluation on an instanc...

Dual Dense Encoding for Zero-Example Video Retrieval

This paper attacks the challenging problem of zero-example video retriev...

Reversible Video Data Hiding Using Zero QDCT Coefficient-Pairs

There exist many zero quantized discrete cosine transform (QDCT) coeffic...

Self-supervised Video Retrieval Transformer Network

Content-based video retrieval aims to find videos from a large video dat...

Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning

In this work, we address the problem of audio-based near-duplicate video...

Examining Representational Similarity in ConvNets and the Primate Visual Cortex

We compare several ConvNets with different depth and regularization tech...

Password similarity using probabilistic data structures

Passwords should be easy to remember, yet expiration policies mandate th...

Please sign up or login with your details

Forgot password? Click here to reset