Wonyoung Yoo

Design and implementation of fingerprinting-based broadcasting content identification system

The existing fingerprinting technologies are not appropriate for broadcasting content identification services which identify broadcasting content in real-time because of the low fingerprint extraction speed and long DB update time. Thus, to apply fingerprinting to the second screen service, it needs a fingerprinting technology which can extract fingerprint while playing the content and update fingerprint DB in real-time. In this paper, we propose a fingerprint-based second screen framework which can identify broadcasting content in real time by on-time content identifier. We define this fingerprint as on-time identifier, and content identification system using on-time identifier as the identification system.

Robust video fingerprinting based on hierarchical symmetric difference feature

The piracy of copyrighted digital content over the Internet infringes copyrights and damages the digital content industry. Accordingly, identifying and monitoring technology on the online content service like fingerprinting is getting valuable through the explosion of digital content sharing. This paper proposes a robust video fingerprinting feature to identify a modified video clip from a large scale database. Hierarchical symmetric difference feature is proposed in order to offer efficient video fingerprinting. The feature is robust and pairwise independent against various video modifications such as compression, resizing, or cropping. Moreover, videos undergoing a transformation such as flipping or mirroring can be identified by simply disordering the bit pattern of fingerprints. The performance of the proposed feature is extensively experimented on 6,482 hours of database and the experimental results show that the proposed fingerprinting is efficient and robust against various modifications.

Steganalytic Measures for the Steganography Using Pixel-Value Differencing and Modulus Function

The steganalytic measures are proposed to destroy the steganographic method using pixel-value differencing(PVD) and modulus function. The modulus PVD steganography method utilizes the remainder of the two consecutive pixels to embed the secret data, which gains more flexibility and is capable of deriving the optimal remainder of the two pixels at the least distortion. However, there exist unavoidable weaknesses: fluctuation of the histogram, asymmetry of the 1 and -1 histogram values, and abnormal increasing of the 0 histogram value. The steganalytic measures are designed using these weaknesses of the modulus PVD steganography method. Through experiments, we prove that the proposed steganalytic measures successfully defeat the modulus PVD steganography method.

Improved Watermark Estimation Scheme Based on Neighborhood Filter

This paper introduces a new watermark estimation scheme for an additive watermark embedding model in spatial domain. Unlike traditional estimating filters only considering spatially adjacent pixels, the proposed method takes into account pixels which are both in close intensity value and spatially near distance. Thus, it is possible for the proposed method to estimate stably the watermark signal from a watermarked image that severely fluctuates in intensity value. Also, this paper proposes the preprocessing method that boosts the performance of our watermark estimation filter by suppressing host signal noises. Extensive experimental results show that the proposed method outperforms the traditional filters under various attacks.

An identification system using fingerprint for live broadcasting content On TV

We propose a new identification system for live broadcasting content on TV in this paper. We exploit fingerprinting scheme for audio or video sequences to identify broadcasting content. Moreover, we decrease delay time after inserting fingerprint on DB in order to improve efficiency of a proposed system. The proposed system is composed of a registration server per one TV channel, an identification server with a director and workers, and many search clients. Simulation results show that the proposed system provides real-time processing performance on live broadcasting content on TV.

Chroma Feature Abstraction using Multiscale 2D-FTM and N-gram for Cover Song Search

We proposed a chroma feature sequence abstraction method that can, when compared with conventional methods, improve the speed of cover song identification methods so that it can be used in large-scale music identification services. The proposed method represents the chroma feature sequence, which is proportional to the length of music, in fixed length feature vectors using multiscale 2D-FTM (two-dimensional Fourier-transform magnitude) and chroma n-gram. It facilitates indexing and simplifies distance comparison to improve identification speed. The abstracted chroma vector maintains the global and local characteristics of the chroma feature sequence, making it more robust to the tempo change, transposition, and remake versions of a song. We experimented using public datasets and large-scale datasets collected from the YouTube website in order to verify the performance of the proposed method, and we confirmed that search speed was improved while maintaining the cover song identification performance.

Soccer event recognition technique based on pattern matching

Recently, there has been an increasing number of attempts to analyze sport activities through the combination of sports science and ICT technology. In the case of soccer, several leading companies have already developed tracking techniques for players to automatically acquire sports analysis data. However, the automatic extraction of event data for analyzing the sports games is limited to the level of academic research, and the field still depends on the manual work of professional analysts. This paper proposes a soccer event recognition technology based on pattern matching. As can be seen from the experimental results, it is possible to recognize various events much more accurately than the event recognition technology at academic research level.

TF-IDF based binary fingerprint search with vector quantization error compensation

In this paper, we propose a TF-IDF based binary fingerprint search scheme which compensates the vector quantization error. Our fingerprinting scheme purposes on supporting the search for a large scale of multimedia data, with tens or hundreds billions of fingerprint. We consider sets of index candidates to compensate the quantization error. In the proposed scheme, index data and fingerprint data are managed differently for a large scale of content search. Index data is managed with in-memory storage while fingerprint data is managed with the traditional DB and in-memory cache.

Which is the best quality video

As video consumption becomes popular, demand for high quality of experience of consumed videos is also increasing. Moreover, the need for duplicate video file management has rapidly increased depending on the quality. While online video sharing is popular, quality assessment of videos is challenging due to lack of reference videos and simultaneous involvement of diverse quality factors. In this paper, we propose a no-reference visual quality assessment method for various kinds of video. The method combines two types of measure to predict the visual quality score. One is the sharpness factors, which are related to the edge regions of video frames, and the other is the overall distortions. We show experimental results for quality assessment accuracy of video.

Professional and amateur-produced video classification for copyright protection

The illegal sharing problem of copyrighted video content such as a movie and TV program through the cloud storage is emerging as important issue. The fingerprint-based identification method can recognize the copyright information of the clip to share and restrict the sharing of copyrighted video. However the only video file pre-registered in the fingerprint DB can be recognized and non-registered ones are exposed to illegal sharing files. The copyrighted video like a film and TV program are almost produced by professionals and personal clips such as home video are made by amateurs. In this paper, we propose professional and amateur-produced video classification for video file sharing control on cloud storage.