Robust video copy detection based on ring decomposition based binarized statistical image features and invariant color descriptor (RBSIF-ICD).
Saved in:
| Title: | Robust video copy detection based on ring decomposition based binarized statistical image features and invariant color descriptor (RBSIF-ICD). |
|---|---|
| Authors: | Himeur, Yassine1 yhimeur@cdta.dz, Sadi, Karima Ait1 aitsaadi@cdta.dz |
| Source: | Multimedia Tools & Applications. Jul2018, Vol. 77 Issue 13, p17309-17331. 23p. |
| Subjects: | Content-based image retrieval, Copyright of video recordings, Video recording piracy, Business intelligence, Statistical methods in image analysis, Image recognition (Computer vision), Texture analysis (Image processing), Robust control |
| Abstract: | Content based video copy detection (CBVCD) is considered as an active research field due to the requirement of copyright protection, business intelligence, video retrieval, etc. In this paper, we propose a CBVCD scheme using Ring decomposition based Binarized Statistical Image Features (RBSIF) and Invariant Color Descriptor (ICD), namely RBSIF-ICD. This hybrid descriptor is based on the combination of texture features extracted using RBSIF and a color characteristics derived using ICD. Firstly, a pre-processing is applied on each video sequence to remove borders. Secondly, the RBSIF descriptor is applied to each video frame to obtain the texture features. Then, ICD is applied to the video frames to construct an invariant color description which is very robust to geometrical attacks. Finally, RBSIF and ICD are fused to develop the RBSIF-ICD that will be very robust against several attacks such as rotation, flipping, strong compression,... etc. For the evaluation purpose, the TRECVID 2009 database is used to test the robustness of the proposed system. Experiments reveal that the proposed RBSIF-ICD system outperforms the state-of-the-art algorithms under all the attacks and manipulations considered in this framework. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Content based video copy detection (CBVCD) is considered as an active research field due to the requirement of copyright protection, business intelligence, video retrieval, etc. In this paper, we propose a CBVCD scheme using Ring decomposition based Binarized Statistical Image Features (RBSIF) and Invariant Color Descriptor (ICD), namely RBSIF-ICD. This hybrid descriptor is based on the combination of texture features extracted using RBSIF and a color characteristics derived using ICD. Firstly, a pre-processing is applied on each video sequence to remove borders. Secondly, the RBSIF descriptor is applied to each video frame to obtain the texture features. Then, ICD is applied to the video frames to construct an invariant color description which is very robust to geometrical attacks. Finally, RBSIF and ICD are fused to develop the RBSIF-ICD that will be very robust against several attacks such as rotation, flipping, strong compression,... etc. For the evaluation purpose, the TRECVID 2009 database is used to test the robustness of the proposed system. Experiments reveal that the proposed RBSIF-ICD system outperforms the state-of-the-art algorithms under all the attacks and manipulations considered in this framework. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-017-5307-4 |
