• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.261-268
• /
• 2015

In spoken chatting systems, users'spoken queries are converted to text queries using automatic speech recognition (ASR) engines. If the top-1 results of the ASR engines are incorrect, these errors are propagated to the spoken chatting systems. To improve the top-1 accuracies of ASR engines, we propose a post-processing model to rearrange the top-n outputs of ASR engines using a ranking support vector machine (RankSVM). On the other hand, a number of chatting sentences are needed to train chatting systems. If new chatting sentences are not frequently added to training data, responses of the chatting systems will be old-fashioned soon. To resolve this problem, we propose a data collection model to automatically select chatting sentences from TV and movie scenarios using a support vector machine (SVM). In the experiments, the post-processing model showed a higher precision of 4.4% and a higher recall rate of 6.4% compared to the baseline model (without post-processing). Then, the data collection model showed the high precision of 98.95% and the recall rate of 57.14%.

• Science of Emotion and Sensibility
• /
• v.18 no.1
• /
• pp.103-110
• /
• 2015

Sentiment lexicon is an essential element for expressing sentiment on a text or recognizing sentiment from a text. We propose a graph-based semi-supervised learning method to construct a sentiment dictionary as sentiment lexicon set. In particular, we focus on the construction of domain-specific sentiment dictionary. The proposed method makes up a graph according to lexicons and proximity among lexicons, and sentiments of some lexicons which already know their sentiment values are propagated throughout all of the lexicons on the graph. There are two typical types of the sentiment lexicon, sentiment words and sentiment phrase, and we construct a sentiment dictionary by creating each graph of them and infer sentiment of all sentiment lexicons. In order to verify our proposed method, we constructed a sentiment dictionary specific to the movie domain, and conducted sentiment classification experiments with it. As a result, it have been shown that the classification performance using the sentiment dictionary is better than the other using typical general-purpose sentiment dictionary.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.1
• /
• pp.39-44
• /
• 2009

The advance of communication and networking technology enables high bandwidth multimedia data transmission. The development of high performance compression technology such as H.264 also encourages high quality video and audio data transmission. The trend requires efficient protection system for digital media rights. We propose an efficient digital media protection system using elliptic curve cryptography. Only key parameters are encrypted to reduce the burden of complex encryption and decryption in the proposed system, and the digital media are not played back or the quality is degraded if the encrypted information is missing. We need a playback system with an ECC processor to implement the proposed system. We implement an H.264 decoding system with a configurable ECC processor to verify the proposed protection system We verify that the H.264 movie is not decoded without the decrypted information.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.414-419
• /
• 2008

3D rendering is a critical process for a movie production, advertisement, interior simulation, medical and many other fields. Recently, several effective rendering methods have been developed for the photo-realistic image generation. With a rapid performance enhancement of graphics hardware, physically based 3D rendering algorithm can now often be approximated in real-time games. However, the high quality of global illumination, required for the image generation in the 3D animation production community is a still very expensive process. In this paper, we propose a new rendering method to create photo-realistic global illumination effect efficiently by harnessing the high power of the recent GPUs. Final gathering routines in our global illumination module are accelerated by programmable graphics hardware. We also simulate physically based light transport on a ray tracing based rendering algorithm with photon mapping effectively.

• Journal of Internet Computing and Services
• /
• v.6 no.3
• /
• pp.129-145
• /
• 2005

This paper proposes the web information extraction system that extracts the pre-defined information automatically from web documents (i.e, HTML documents) and integrates the extracted information, The system recognizes entities without lables by the probabilistic based entity recognition method and extends the existing domain knowledge semiautomatically by using the extracted data, Moreover, the system extracts the sub-linked information linked to the basic page and integrates the similar results extracted from heterogeneous sources, The experimental result shows that the system extracts the sub-linked information and uses the probabilistic based entity recognition enhances the precision significantly against the system using only the domain knowledge, Moreover, the presented system can the more various information precisely due to applying the system with flexibleness according to domains, Because bath the semiautomatic domain knowledge expansion and the probabilistic based entity recognition improve the quality of the information, the system can increase the degree of user satisfaction at its maximum. Thus, this system can satisfy the intellectual curiosity of users from movie sites, performance sites, and dining room sites, We can construct various comparison shopping mall and contribute the revitalization of e-business.

• Journal of Broadcast Engineering
• /
• v.18 no.1
• /
• pp.31-42
• /
• 2013

This paper proposes a photogrammetric rectification method based on Bayesian approach as a method that eliminates vertical parallax between stereo images to minimize visual fatigue of 3D contents. The image rectification consists of two phases; geometry estimation and epipolar transformation. For geometry estimation, coplanarity-based relative orientation algorithm was used in this paper. To ensure robustness for mismatch and localization error occurred by automation of tie point extraction, Bayesian approach was applied by introducing several prior constraints. As epipolar transformation perspective transformation was used based on condition of collinearity to minimize distortion of result images and modification for input images. Other algorithms were compared to evaluate performance. For geometry estimation, traditional relative orientation algorithm, 8-points algorithm and stereo calibration algorithm were employed. For epipolar transformation, Hartley algorithm and Bouguet algorithm were employed. The evaluation results showed that the proposed algorithm produced results with high accuracy, robustness about error sources and minimum image modification.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2004.05a
• /
• pp.156-160
• /
• 2004

Our time is called as the era of information-oriented society and up-to-date scientific technology, but it can be also called as the era of image. It is because the image has much influence upon our everyday life. In the deluge of images, the delivery of image Is a better and faster synergic tool than the delivery of language, and this trend is consistent with the phases of the times in which the analog modality of synergy is converted into the digital one. The image is a picture that is formed by a physical process, and is all the figures reflected by electronic equipments that reproduce the image. After the discovery of photograph in 1893, the image has been appeared first with the form of movie, and then with the form of TV. However, the appearance of such unidirectional synergic tools as movies and TV. has provided artists with some creative motives with which they intercommunicate their messages via some experimental bidirectional synergic tools. Among image-media arts, the performance of installation and participation is an important example that causes many changes through conceptional conversion, such as the conception of the time in space and formative characteristics. What satisfy this trend have been videos, lasers, holographic, and etc. Furthermore, the appearance of computer has provided a synesthesia, that is, a virtual reality, and mixed a real image with a visional one. The image-media art will realize better synergy through combining brand new machines, informational technology, and art, and have much influence upon our everyday life formatively and artistically in the future. with this study, through analyzing the meaning of relationship between image equipments and space.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.4
• /
• pp.282-288
• /
• 2014

Three-dimensional multimedia industry such as 3D TV, movie and broadcast has been developed vividly. For generating 3D contents with high quality, virtual auditory display, so called VAD, is being researched to offer more realistic experience to listeners. When people render VAD using headphones or two speakers, head-related transfer function(HRTF) plays a key role. The best solution is measuring all individuals' HRTFs, but it is hard to measure all listeners' HRTFs. To overcome this difficulty, many research groups have tried to construct their own measurement system and to build HRTF databases. However, some of them have not enough subjects or spatial resolution and they are mainly focused on Caucasian. There exists difference between Korean and Caucasian in a view of physical features. In other words, if Koreans hear three-dimensional sound rendered by HRTF database based on Caucasian, performance might be hindered. To verify this possibility and remedy the drawbacks, construction of new HRTF database aimed at Korean is needed. Therefore, our laboratory built HRTF measurement system which can measure HRTF of three-dimensional space with dense spatial resolution. With this system, 55 Korean males and 45 females' HRTFs were measured and Korean HRTF database was built based on these data.

• Journal of Broadcast Engineering
• /
• v.7 no.3
• /
• pp.211-218
• /
• 2002

This paper introduces the HD 3DTV camera and 3DTV receiver that are compatible with the ATSC HDTV broadcasting system. The developed 3DTV camera is based on stereoscopic techniques, and it has control function to control both left and right zoom lens simultaneously and to control the vergence. Moreover, in order to control the vergence manually and to eliminate the synchronization problem of the both images, the 3DTV camera has the 3DTV video multiplexing function to combine the left and right images into the single image. The developed 3DTV signal, and it has the various analog/digital interfaces. The performance of the developed system is confirmed by shooting the selected soccer game in 2002 FIFA KOREA/JAPANTM World Cup and by broadcasting the match. The HD 3DTV camera and receiver will be applied to the 3DTV industries such as 3D movie, 3D game, 3D image processing, 3DTV broadcasting system, and so on.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1059-1067
• /
• 2011

Next-Generation ITS environment requires high-speed data packet transmission, security, authentication, and hand-over supportable for driving vehicle on road by installing RSEs and OBUs. Therefore, wireless communication technology for next-generation ITS services are advancing to 200km/h maximum speed supportable, 1km communication radius, minimum 10Mbps hish-speed datarate for multimedia data(such as text, images, movie clips and so on) supportable, high reliability. In this paper, we implemented WAVE communication system which based on IEEE 802.11p PHY/MAC and evaluated that the system meets next-generation ITS environments.