• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1263-1272
• /
• 2004

In this paper, we present a novel video fingerprinting implementation method to identify the source of illegal copies. The video fingerprinting is achieved by the insertion of uniform distributed random number is made by seller and buyer's identification key-in the video wavelet coefficients by their temporal wavelet transform. The proposed fingerprinting is able to detect unique fingerprint of video contents even if they have been distorted by collusion attacks and MPEG2 compression. Especially, we use characteristics of the temporal wavelet transform to assign user's embedding area. Experimental results show the traceability of unauthorized distribution of video contents and its robustness to various collusion attacks and MPEG2 compression.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.64-73
• /
• 2012

In this paper, we propose a method to search for identical videos. The proposed method is spatio-temporal group feature fingerprinting. Frame of video is extracted from fixed rate method and is partitioned into vertical group and horizontal group. Descriptor is made of each group feature that is extracted from binary fingerprinting. Next, use descriptor of original video to build a two type of fingerprinting database and matching with query video. To efficient and effective video copy detection, method have high robustness, independence, matching speed. In proposed method, group feature have high robustness and independence in variable modification of video. Building a original fingerprinting database is able to fast matching with query video. The proposed method shows performance improvement in variable modifications in comparison to the existing methods. Especially, very singular performance in speed improvement is great advantage of this paper.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.443-450
• /
• 2005

Digital fingerprinting is a contents-protection technique, where customer information is inserted into digital contents. Fingerprinted contents undergo various attacks. Especially, attackers can remove easily the inserted fingerprint by collusion attacks, because digital fingerprinting inserts slightly different codes according to the customers. Among collusion attacks, averaging attack is a simple, fast, and efficient attack. In this paper, we propose a video fingerprinting system that is robust to the averaging attack. In order to achieve code efficiency and robustness against the averaging attack, we adopt anti-collusion code (fingerprint code) from GD-PBIBD theory. When the number of users is increased, the size of fingerprint code also grows. Thus, this paper addresses a zero-based code modulation technique to embed and detect this fingerprint code efficiently. We implemented a blind video fingerprinting system based on our proposed technique and performed experiments on various colluding cases. Based on the results, we could detect most of colluders. In the worst case, our scheme could trace at least one colluder successfully.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.62 no.4
• /
• pp.204-209
• /
• 2013

FFT based fingerprinting to conceal more information has developed for video copyright protection. More complex information of video is necessary to prove an ownership and legal distributions in invisible form. This paper describes a method to insert more information and to detect them. $3{\times}3$ points structure is used to present information. The possible ways to show are 8bit, $2^8$ = 256 where one point of 9 is always turn on. The points are marked in frequency domain that both real and imaginary party numbers are modified. The five successive frames of same scenes are used to mark because the same scene has very similar shape in FFT result. However, the detail values of coefficients are totally different each other to recognize the marked points. This paper also describes a method to detect the marked points by averaging and correlation algorithm. The PSNRs of marked images by our method had 51.138[dB] to 51.143[dB]. And we could get the correlation values from 0.79 to 0.87.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.15-21
• /
• 2010

This paper proposes the multimedia fingerprinting code insertion algorithm when video content is distributed in P2P environment, and designs the collusion codebook SRP(Small RISC Processor) embedded system for the collusion attack prevention. In the implemented system, it is detecting the fingerprinting code inserted in the video content of the client user in which it requests an upload to the web server and in which if it is certified content then transmitted to the streaming server then the implemented system allowed to distribute in P2P network. On the contrary, if it detects the collusion code, than the implemented system blocks to transmit the video content to the streaming server and discontinues to distribute in P2P network. And also it traces the colluders who generate the collusion code and participates in the collusion attack. The collusion code of the averaging attack is generated with 10% of BIBD code v. Based on the generated collusion code, the codebook is designed. As a result, when the insert quantity of the fingerprinting code is 0.15% upper in bitplane 0~3 of the Y(luminance) element of I-frame at the video compression of ASF for a streaming service and MP4 for an offline offer of video content, the correlation coefficient of the inserted original code and the detected code is above 0.15. At the correlation coefficient is above 0.1 then the detection ratio of the collusion code is 38%, and is above 0.2 then the trace ratio of the colluder is 20%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.4
• /
• pp.885-894
• /
• 2016

As smartphones become more common, anybody can take pictures and record videos easily nowadays. Video files taken from smartphones can be used as important clues and evidence. While you analyze video files taken from smartphones, there are some occasions where you need to prove that a video file was recorded by a specific smartphone. To do this, you can utilize various fingerprint techniques mentioned in existing research. But you might face the situation where you have to strengthen the result of fingerprinting or fingerprint technique can't be used. Therefore forensic investigation of the smartphone must be done before fingerprinting and the database of metadata of video files should be established. The artifacts in a smartphone after video recording and the database mentioned above are discussed in this paper.

• ETRI Journal
• /
• v.32 no.3
• /
• pp.490-492
• /
• 2010

This letter proposes a robust feature extraction method using a spatially normalized mean for temporal ordinal measurement. Before computing a rank matrix from the mean values of non-overlapped blocks, each block mean is normalized so that it obeys the invariance property against linear additive and subtractive noise effects and is insensitive against multiplied and divided noise effects. Then, the temporal ordinal measures of spatially normalized mean values are computed for the feature matching. The performance of the proposed method showed about 95% accuracy in both precision and recall rates on various distortion environments, which represents the 2.7% higher performance on average compared to the temporal ordinal measurement.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.36-39
• /
• 2003

본 논문에서는 비디오 컨텐츠 내에 소유자와 구매자 정보를 함께 포함하는 핑거프린팅 정보를 삽입하여 불법으로 배포된 핑거프린팅 컨텐츠로부터 배포자가 누구인지를 추적할 수 있는 기법을 보인다. 특히, 문헌[1]에서 제시된 시간축 웨이블릿 변환을 이용하여 핑거프린팅 정보가 삽입될 영역을 분리해 주고, 역 변환을 통해 전 영역의 비디오 프레임에 정보가 삽입되게 된다. 이로 인해 핑거프린팅된 컨텐츠의 상이성을 이용한 기존의 여러 공모공격에도 강인함을 보이고 있다. 또한, 비디오 컨텐츠의 특성상 MPEG2의 압축에도 불법 배포자를 추적할 수 있는 강인함을 보인다.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.743-753
• /
• 2020

In this paper, we propose a set of robustness indicators for immersive 360-degree video. With the full-fledged service of mobile carriers' 5G networks, it is possible to use large-capacity, immersive 360-degree videos at high speed anytime, anywhere. Since it can be illegally distributed in web-hard and torrents through DRM dismantling and various video modifications, however, evaluation indicators that can objectively evaluate the filtering performance for copyright protection are required. In this paper, a robustness indicators is proposed that applies the existing 2D Video robustness indicators and considers the projection method and reproduction method, which are the characteristics of Immersive 360-degree Video. The performance evaluation experiment has been carried out for a sample filtering system and it is verified that an excellent recognition rate of 95% or more has been achieved in about 3 second execution time.