SW Content Research Laboratory

Daejeon, South Korea

SW Content Research Laboratory

Daejeon, South Korea
Time filter
Source Type

Yoo J.-H.,SW Content Research Laboratory | Kang B.J.,Hyundai Mobis
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops | Year: 2014

We describe an image acquisition system based on an integrated dual-sensor with a visible and infrared spectrum, which enables a multimodal biometric system, including non-intrusive iris recognition. To implement this as capable of simultaneously acquiring facial and iris images, a beam splitter for reflecting or transmitting visible and infrared light representing an image of a target object is used along an identical ray path divided into different bands. Namely, the beam splitter divides incident light from an object into the dual-sensor. Accordingly, an image of the iris area and an image of the facial region can be simultaneously acquired from a single image acquisition system, and an iris image can be acquired from a relatively long distance. The iris biometric system is implemented by using the facial detection and iris recognition SDK. In experiments, we have successfully evaluated the performance of the proposed image acquisition system with a non-intrusive iris recognition algorithm. © 2015 IEEE.

Youn T.-Y.,SW Content Research Laboratory | Chang K.-Y.,SW Content Research Laboratory
ETRI Journal | Year: 2014

Fairness of exchange is a significant property for secure online transactions, and a fair exchange scheme is a useful tool for ensuring the fairness of exchanges conducted over networks. In this paper, we propose an ID-based optimistic fair exchange scheme based on the RSA function, one which is designed by combining a wellknown RSA-based signature scheme and the (naive) RSA function. Note that the main contribution of this paper is to give the first provably secure ID-based fair exchange scheme based on the RSA function, whose security can be proved under fully formalized security models. Our scheme has the following additional strongpoints. The scheme is setup-free; hence, there is no registration step between a user and an arbitrator. Moreover, the proposed scheme is designed in an ID-based setting; thus, it is possible to eliminate the need for certificates and avoid some related problems. © 2014 ETRI.

Lee S.J.,SW Content Research Laboratory | Lee S.J.,Korean University of Science and Technology | Kang B.O.,SW Content Research Laboratory | Kang B.O.,Korean University of Science and Technology | And 4 more authors.
ETRI Journal | Year: 2014

In this paper, alternative dynamic features for speech recognition are proposed. The goal of this work is to improve speech recognition accuracy by deriving the representation of distinctive dynamic characteristics from a speech spectrum. This work was inspired by two temporal dynamics of a speech signal. One is the highly non-stationary nature of speech, and the other is the inter-frame change of a speech spectrum. We adopt the use of a sub-frame spectrum analyzer to capture very rapid spectral changes within a speech analysis frame. In addition, we attempt to measure spectral fluctuations of a more complex manner as opposed to traditional dynamic features such as delta or double-delta. To evaluate the proposed features, speech recognition tests over smartphone environments were conducted. The experimental results show that the feature streams simply combined with the proposed features are effective for an improvement in the recognition accuracy of a hidden Markov model-based speech recognizer. © 2014 ETRI.

Park S.I.,Sejong University | Lim S.-J.,SW Content Research Laboratory
ETRI Journal | Year: 2014

In this paper, we present a method for reconstructing a surface mesh animation sequence from point cloud animation data. We mainly focus on the articulated body of a subject - the motion of which can be roughly described by its internal skeletal structure. The point cloud data is assumed to be captured independently without any inter-frame correspondence information. Using a template model that resembles the given subject, our basic idea for reconstructing the mesh animation is to deform the template model to fit to the point cloud (on a frame-by-frame basis) while maintaining inter-frame coherence. We first estimate the skeletal motion from the point cloud data. After applying the skeletal motion to the template surface, we refine it to fit to the point cloud data. We demonstrate the viability of the method by applying it to reconstruct a fast dancing motion. © 2014 ETRI.

Bae Y.,SW Content Research Laboratory | Bae Y.,Korean University of Science and Technology | Ryu P.-M.,SW Content Research Laboratory | Kim H.,SW Content Research Laboratory
ETRI Journal | Year: 2014

In social network services, such as Facebook, Google+, Twitter, and certain postings attract more people than others. In this paper, we propose a novel method for predicting the lifespan and retweet times of tweets, the latter being a proxy for measuring the popularity of a tweet. We extract information from retweet graphs, such as posting times; and social, local, and content features, so as to construct prediction knowledge bases. Tweets with a similar topic, retweet pattern, and properties are sequentially extracted from the knowledge base and then used to make a prediction. To evaluate the performance of our model, we collected tweets on Twitter from June 2012 to October 2012. We compared our model with conventional models according to the prediction goal. For the lifespan prediction of a tweet, our model can reduce the time tolerance of a tweet lifespan by about four hours, compared with conventional models. In terms of prediction of the retweet times, our model achieved a significantly outstanding precision of about 50%, which is much higher than two of the conventional models showing a precision of around 30% and 20%, respectively. © 2014 ETRI.

Nidaw B.Y.,SW Content Research Laboratory | Shin Z.,SW Content Research Laboratory | In J.S.,SW Content Research Laboratory | Woo K.Y.,SW Content Research Laboratory
International Conference on Advanced Communication Technology, ICACT | Year: 2016

These days the number of processors in computer systems is increasing in a very fast speed, and different manufacturers are producing computers with manycore processors. In turn, these manycore processor computer systems require a new operating system that can solve the problems of commodity operating systems. Commodity operating systems originally made for a single, dual or multi-cores systems; they will have lower performance and scalability problem for higher number of cores that are hundreds or thousands in number. In this regard, scholars of different research institutions are trying to develop their own solutions for existing problems among commodity operating systems and the recently emerging the manycore processor. This paper intends to see what those manycore operating systems are. The main objective of this paper is to compare and contrast some of manycore operating systems, analyze their experimental results, and give some summarizing concepts. Manycore operating systems are developing either from the scratch or the amendment on the existing commodity operating systems. Operating systems projects that develop a manycore operating system from the scratch, need lots of effort, and generally new approaches are applied. They use completely new technical approaches for development of OSes for increased number of cores. Operating systems like FOS and BarrelFish are some examples of operating systems that developed from the scratch. On the other hand, some operating system projects focus on commodity OSes problems for increased number of cores. These projects amend commodity operating systems and/or used them collectively. Therefore their main task is preparing systems that play an important role for this amendment. As compared with the above operating system development approach, these approaches are simple and more manycore OSes used it. Operating systems like FusedOS, Cerberus and others are such a type of operating systems. In this respect, this paper will see the reason behind the selection of either of the two approaches. Also will provide highlights about the basic structural differences among the existing manycore operating systems, in order to catch the philosophy behind them. © 2016 Global IT Research Institute (GiRI).

Kim J.-H.,SW Content Research Laboratory | Seo Y.-S.,SW Content Research Laboratory | Yoo W.-Y.,SW Content Research Laboratory
International Conference on ICT Convergence | Year: 2014

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. © 2014 IEEE.

Kim J.,SW Content Research Laboratory | Jeong I.-K.,SW Content Research Laboratory
ETRI Journal | Year: 2014

In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider treegrowing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local selfsimilarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease. © 2014 ETRI.

Kang B.O.,SW Content Research Laboratory | Kang B.O.,Chungbuk National University | Kwon O.-W.,Chungbuk National University
IEICE Transactions on Information and Systems | Year: 2016

We propose a new method to combine multiple acoustic models in Gaussian mixture model (GMM) spaces for robust speech recognition. Even though large vocabulary continuous speech recognition (LVCSR) systems are recently widespread, they often make egregious recognition errors resulting from unavoidable mismatch of speaking styles or environments between the training and real conditions. To handle this problem, a multi-style training approach has been used conventionally to train a large acoustic model by using a large speech database with various kinds of speaking styles and environment noise. But, in this work, we combine multiple sub-models trained for different speaking styles or environment noise into a large acoustic model by maximizing the log-likelihood of the sub-model states sharing the same phonetic context and position. Then the combined acoustic model is used in a new target system, which is robust to variation in speaking style and diverse environment noise. Experimental results show that the proposed method significantly outperforms the conventional methods in two tasks: Non-native English speech recognition for second-language learning systems and noise-robust point-of-interest (POI) recognition for car navigation systems. Copyright © 2016 The Institute of Electronics, Information and Communication Engineers.

Yu J.-J.,SW Content Research Laboratory | Park C.-J.,SW Content Research Laboratory
International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015 | Year: 2015

Color discrepancy in stereoscopic images may increase an audience's sense of fatigue when it is played on a 3D display device. Proposed color correction method consists of two phases: a sample-based color matching phase that extracts sample points for color correction and uses a modified histogram mapping with the sample points, followed by an error compensation phase that estimates the quantity of errors induced from a lack of sample points and compensates for errors. Proposed method can match the color tones of left and right images without preprocessing such as rectification or stereo matching, even if the images were captured by different types of cameras with a long base-line and a large convergence. © 2015 IEEE.

Loading SW Content Research Laboratory collaborators
Loading SW Content Research Laboratory collaborators