• 한국멀티미디어학회논문지
• /
• 제12권7호
• /
• pp.1032-1042
• /
• 2009

본 연구는 태깅된 웹 이미지의 검색에서 태그들의 의미정보를 미리 추출하여 검색 시에 이용하고자 하는 것이다. 일반적으로 웹 이미지의 태그들은 사용자들에 의해 순서 구분 없이 무작위로 매겨지며 많게는 그 수가 100여개에 이른다. 본 논문에서는 이 태그들 간에 의미정보가 많이 공유된 것일수록 해당 이미지를 설명하는 중요 태그가 될 것임에 착안하여 이미지와 태그 정보가 업 로드되는 시점에 중요도에 따른 우선 태그를 결정하고 이를 검색에 활용하는 방법을 소개한다 제안된 방법은 워드넷에 기반하여 태그의 연관성점수를 계산하고 이를 이용하여 다단계 검색으로 태징된 웹 이미지를 검색한다. 평가를 위하여 제안된 방법으로 검색된 결과와 검색어와 태그의 단순 비교방식인 기존의 검색을 비교하였으며 실험 결과, 정확도와 재현율에서 본 시스템의 우수함을 확인할 수 있었다.

• 대한전자공학회논문지SP
• /
• 제47권6호
• /
• pp.127-136
• /
• 2010

다시점 비디오는 카메라간의 다른 위치와 불완전한 카메라 보정(calibration)으로 인접한 시점의 영상 내에 존재하는 동일물체 간에 색상 차이가 발생할 수 있다. 이러한 색상 불일치(color mismatch)는 시점 간 움직임 예측(inter-view prediction) 수행 시, 오정합을 발생시켜 다시점 비디오 부호화(Multi-view Video Coding : MVC) 성능을 저하시키는 원인이 된다. 본 논문에서는 이웃하는 영상 간에 존재하는 휘도 및 색차 성분 불일치를 보상하여 다시점 비디오 부호화의 압축률을 향상시키는 전처리 기법을 제안한다. 제안된 기법에서는 모든 시점의 영상을 히스토그램 매칭 기법에 의해 정해진 참조 시점 영상의 색상을 기준으로 보정된다. 또한 히스토그램 매칭 수행 전에 YCbCr 색상공간 변경 시에 색차 성분의 대표 값 추출(chrominance subsampling)에 사용되는 Cosited filter를 영상의 각 색상성분에 적용하여 성능을 더욱 높일 수 있다. 히스토그램 매칭은 YCbCr 색상공간에서 RGB 색상공간으로 변환하여 각 색상성분에 적용한다. 이 과정에서 영상에 존재하는 에지의 방향성과 화소 값의 존재 범위를 고려한 효과적인 색상 변환 기법이 사용된다. 실험을 통해 제안하는 전처리 기법이 다른 기법들에 비해 향상된 부호화 효율을 가지는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권7호
• /
• pp.1657-1670
• /
• 2013

The increase in the number of music files in smart phone and MP3 player makes it difficult to find the music files which people want. So, Query-by-Singing/Humming (QbSH) systems have been developed to retrieve music from a user's humming or singing without having to know detailed information about the title or singer of song. Most previous researches on QbSH have been conducted using musical instrument digital interface (MIDI) files as reference songs. However, the production of MIDI files is a time-consuming process. In addition, more and more music files are newly published with the development of music market. Consequently, the method of using the more common MPEG-1 audio layer 3 (MP3) files for reference songs is considered as an alternative. However, there is little previous research on QbSH with MP3 files because an MP3 file has a different waveform due to background music and multiple (polyphonic) melodies compared to the humming/singing query. To overcome these problems, we propose a new QbSH method using MP3 files on mobile device. This research is novel in four ways. First, this is the first research on QbSH using MP3 files as reference songs. Second, the start and end positions on the MP3 file to be matched are estimated by using multi-layered perceptron (MLP) prior to performing the matching with humming/singing query file. Third, for more accurate results, four MLPs are used, which produce the start and end positions for dynamic time warping (DTW) matching algorithm, and those for chroma-based DTW algorithm, respectively. Fourth, two matching scores by the DTW and chroma-based DTW algorithms are combined by using PRODUCT rule, through which a higher matching accuracy is obtained. Experimental results with AFA MP3 database show that the accuracy (Top 1 accuracy of 98%, with an MRR of 0.989) of the proposed method is much higher than that of other methods. We also showed the effectiveness of the proposed system on consumer mobile device.

• ETRI Journal
• /
• 제27권5호
• /
• pp.628-634
• /
• 2005

From AC analysis results utilizing a 2-dimensional device simulator, we extracted an AC-equivalent circuit of a grounded-gate NMOS (ggNMOS) electrostatic discharge (ESD) protection device. The extracted equivalent circuit is utilized to analyze the effects of the parasitics in a ggNMOS protection device on the characteristics of a low noise amplifier (LNA). We have shown that the effects of the parasitics can appear exaggerated for an impedance matching aspect and that the noise contribution of the parasitic resistances cannot be counted if the ggNMOS protection device is modeled by a single capacitor, as in prior publications. We have confirmed that the major changes in the characteristics of an LNA when connecting an NMOS protection device at the input are reduction of the power gain and degradation of the noise performance. We have also shown that the performance degradation worsens as the substrate resistance is reduced, which could not be detected if a single capacitor model is used.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.557-564
• /
• 2015

There are many prior studies for more natural Human-Computer Interaction. Until now, the efforts is continued in order to recognize motions in various directions. In this paper, we suggest a user-specific recognition by hit detection method using Kinect camera and human proportion. This algorithm extracts the user-specific valid recognition rage after recognizing the user's body initially. And it corrects the difference in horizontal position between the user and Kinect, so that we can estimate a action of user by matching cursor to target using only one frame. Ensure that efficient hand recognition in the game to take advantage of this method of suggestion.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 하계종합학술대회 논문집
• /
• pp.162-165
• /
• 1989

This paper describes an algorithm of P-wave detection by significant point extraction method with digital differentiation. P-waves are detected by pattern matching algorithm with significant points. By means of defecting onset and offset points of P-waves, this algorithm can measure the PR intervals exactly which is important to diagnosis the atrial arrhythmia. Because P-wave duration is changed according to heart-rates, we calculate the R-R interval prior to the determination of P-wave duration threshold values in order to actively adapt to the change of P duration The results obtained from the proposed algorithm have defected successfully P-wave almost more than 90%.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.47-50
• /
• 1995

This paper concerns an adaptive control scheme which is an extension of the simplified adaptive control. Originally, the SAC approach was developed based on the command generator tracker (CGT) theory for perfect model tracking. An attractive point of the SAC is that a control input can be synthesized without any prior knowledge about plant structure. However, a feedforward dynamic compensator of the CGT is removed from the basic structure of the SAC. This deletion of the compensator makes perfect model tracking difficult against even a step input. In this paper, an adaptive control system is redesigned to achieve perfect model tracking for as long as possible by reviving the dynamic compensator of the CGT. The proposed method is applied to slewing control of a flexible space structure and compared to the SAC responses.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.617-618
• /
• 2006

The participants in collaborative environment want to get the right documents which are intended to find. In general search system, it searches documents which contain only the keywords. For searching different word-expressions for the same meaning, we perform mapping before searching. Our mapping logic consists of three steps. First, the character matching is the mapping of two terminologies that have identical character strings. Second, the definition comparing is the method that compares two terminologies' definitions. Third, the similarity checking pairs terminologies which were not mapped by two prior steps. In this paper, we propose Engineering Information Search System based on ontology mapping.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.73-85
• /
• 2009

This paper introduces the technique of synthesizing and evaluating human utterances with exaggerated or atypical prosody. Prosody exaggeration can be implemented by manipulating either the fundamental frequency (F0) contour, the segmental durations, or the intensity contour of an utterance. Of these three prosodic elements, two or more can be exaggerated at the same time. The algorithms of synthesis and evaluation were suggested. Learner utterances exaggerated in each of the three prosodic features were evaluated with respect to their original native versions in terms of the differences in their F0 contours, the segmental durations, and the intensity contours. The measure of differences was the Euclidean distance metric between the matching points in their F0 and intensity contours. The measure was calculated after the exaggerated learner utterances were aligned by the segments and rendered identical to their native version in terms of their segmental durations. For the evaluation of the segmental durations, no prior modifications were made in durations and the same measure was used. The results from the pilot experiment suggest the viability of this measure in the evaluation of learner utterances with atypical prosody with respect to their native versions.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권7호
• /
• pp.872-880
• /
• 1999

This paper presents an algorithm that can calculate the evaluation index of power system from the transfer capability point of view. The algorithm adopts a successive linear programming skill to solve an optimal solution. Two indices which are transfer margin index and economic matching index have been developed. Prior to calculating these indices, Maximum Load supplying Capability(MLSC) and Economic Load Supplying Capability(ELSC) are utilized as basic data. For man-machine interface, graphical user interface has been implemented so that an unified software package PSTCP(Power System Transfer Capability Program) has been developed. KEPCO systems planned up to 2006 year have been tested to show effectiveness and usefulness of the PSTCP for power system planning stages.