• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.226-229
• /
• 2011

얼굴검출기술의 발전으로 인하여, 다양한 분야에 얼굴 검출을 활용한 기술이 이용되고 있다. 최근 Viola 와 Jones 의 얼굴검출 방법이 신뢰도 있는 검출률과 빠른 연산속도로 인하여 주로 이용되고 있다. 하지만 고해상도 이미지와 제한된 하드웨어를 사용하는 시스템의 경우, 실시간 처리가 어려워지는 문제가 있다. 본 논문에서는 이와 같은 문제를 해결하고자 거리 정보를 이용한 빠른 얼굴검출방법을 제안한다. 속도 개선을 위해 먼저 거리 정보를 이용하여 영상의 불필요한 부분을 제거하고, 피부색상정보를 이용하여 관심영역을 설정한다. 또 크기에 대응하기 위해 피라미드 이미지를 이용하는 방법 대신, 거리 정보를 이용하여 얼굴의 크기를 추정한다. 마지막으로 검색창 내의 거리 분산을 계산하여, 평평하거나 굴곡이 심한 영역을 제거함으로 얼굴 검출 속도를 개선하였다. 실험결과 기존 방법에 비해 더 빠른 검출속도와 유사한 검출성능을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.4
• /
• pp.266-272
• /
• 2012

Speaker segmentation is a process of automatically detecting the speaker boundary points in the audio data. Speaker segmentation methods are divided into two categories depending on whether they use a prior knowledge or not: One is the model-based segmentation and the other is the metric-based segmentation. In this paper, we introduce the eigenvoice-based speaker weight distance method and compare it with the representative metric-based methods. Also, we employ and compare the Euclidean and cosine similarity functions to calculate the distance between speaker weight vectors. And we verify that the speaker weight distance method is computationally very efficient compared with the method directly using the distance between the speaker adapted models constructed by the eigenvoice technique.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.37-46
• /
• 2013

Similarity measure of catchments is essential for regionalization studies, which provide in depth analysis in hydrological response and flood estimations at ungauged catchments. However, this similarity measure is often biased to the selected catchments and is not clearly explained in hydrological sense. This study applied a type of hydrological similarity distance measure-Flood Estimation Handbook to 25 Geum River catchments, Korea. Three Catchment Characteristics, Area(A)-Annual precipitation(SAAR)-SCS Curve Number(CN), are used in Euclidian distance measures. Furthermore, six index of Flow Duration Curve are applied to clustering analysis of SPSS. The catchments' grouping of hydrological similarity measures suggests three groups (H1, H2 and H3) and the four catchments are not grouped in this study. The clustering analysis of FDC provides four Groups; F1, F2, F3 and F4. The six catchments (out of seven) of H1 are grouped in F1, while Sangyeogyo is grouped in F2. The four catchments (out of six) of H2 are also grouped in F2, while Cheongju and Guryong are grouped in F1. The catchments of H3 are categorized in F1. The authors examine the results (H1, H2 and H3) of similarity measure based on catchment physical descriptors with results (F1 and F2) of clustering based on catchment hydrological response. The results of hydrological similarity measures are supported by clustering analysis of FDC. This study shows a potential of hydrological catchment similarity measures in Korea.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.22 no.3
• /
• pp.187-194
• /
• 2002

This study was carried out to investigate the ecological characteristics, forage value and similarity among the plant communities of the gazing pasture at Witzenhausen, Germany. Ten plant communities of the different grazing pasture were the Molinio-Arrhenatheretea that was named the class of plant sociological nomenclature. The forage value of the plant communities were ranged from 4.35 to 6.60 grade for roughage qualify. Hemicryptophyte of lift form and mesomorphic of anatomical structure were greately dominated in all the plant communities. The correlation coeffcient between class No. 3 and 4 of plant communities was highest by botanical composition. The clustering analysis by Euclidean distance showed that class No. 9 and 10 of plant communities were closely grouped as affected by the similar botanical composition.

• The KIPS Transactions:PartD
• /
• v.15D no.1
• /
• pp.31-40
• /
• 2008

We generally use lower-dimensional transformations to convert high-dimensional sequences into low-dimensional points in similar sequence matching. These traditional transformations, however, show different characteristics in indexing performance by the type of time-series data. It means that the selection of lower-dimensional transformations makes a significant influence on the indexing performance in similar sequence matching. To solve this problem, in this paper we propose a hybrid approach that integrates multiple transformations and uses them in a single multidimensional index. We first propose a new notion of hybrid lower-dimensional transformation that exploits different lower-dimensional transformations for a sequence. We next define the hybrid distance to compute the distance between the transformed sequences. We then formally prove that the hybrid approach performs the similar sequence matching correctly. We also present the index building and the similar sequence matching algorithms that use the hybrid approach. Experimental results for various time-series data sets show that our hybrid approach outperforms the single transformation-based approach. These results indicate that the hybrid approach can be widely used for various time-series data with different characteristics.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.289-291
• /
• 2003

3차원 형상 모델의 비교 연구는 의학, 분자 생물학, 컴퓨터 그래픽스 등의 분야에서 다루게 되는 기본적인 문제들 중의 하나이다. 본 논문에서는 3차원 형상 모델간의 유사성을 측정하기 위한 방법을 제안한다. 본 시스템은 삼각형 메쉬 모델을 유사성 평가에 사용한다. 유사성 비교를 위해 실루엣 영상을 이용하고, 유사 점도의 계산을 위한 측도(metric)로는 부피(Volume), 곡률(Curvature), 직선거리(Euclidean Distance)를 사용한다. 또한 다양한 방식에 의해 획득된 형상 모델의 비교를 위하여 먼저 포즈 정규화(Pose Normalization)를 한 후 유사성 평가 작업을 수행한다. 본 논문에서 제시한 3차원 형상 비교 시스템은 형상 비교대상들에 대한 전체 변형 및 부분 변형, 그리고 회전등에 강인함을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.162-166
• /
• 2020

자연어 이해는 대화 인터페이스나 정보 추출 등에 활용되는 핵심 기술 중 하나이다. 최근 딥러닝을 활용한 데이터 기반 자연어 이해 연구가 많이 이루어지고 있으며, 이러한 연구에 있어서 데이터 확장은 매우 중요한 역할을 하게 된다. 본 연구는 자연어 이해영역에서의 말뭉치 혹은 데이터 확장에 있어서, 입력으로 주어진 문장과 문법구조 및 의미가 유사한 문장을 생성하는 새로운 방법을 제시한다. 이를 위해, 우리는 GPT를 이용하여 대량의 문장을 생성하고, 문장과 문장 사이의 문법구조 및 의미 거리 계산법을 제시하여, 이를 이용해 가장 유사하지만 새로운 문장을 생성하는 방법을 취한다. 한국어 말뭉치 Weather와 영어 말뭉치 Atis, Snips, M2M-Movie M2M-Reservation을 이용하여 제안방법이 효과적임을 확인하였다.

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.409-419
• /
• 2007

Database community focuses on the similar music retrieval systems for music database when a humming query is given. One of the approaches is converting the midi data to time series, building their indices and performing the similarity search on them. Queries based on humming can be transformed to time series by using the known pitch detection algorithms. The recently suggested algorithm, scaled and warped matching, is based on dynamic time warping and uniform scaling. This paper proposes Humming BIRD(Humming Based sImilaR mini music retrieval system) using sliding window and center-aligned scaled and warped matching. Center-aligned scaled and warped matching is a mixed distance measure of center-aligned uniform scaling and time warping. The newly proposed measure gives tighter lower bound than previous ones which results in reduced search space. The empirical results show the superiority of this algorithm comparing the pruning power while it returns the same results.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.147-152
• /
• 2007

Face detection is a crucial part of the face recognition system. It determines the performance of the whole recognition system. Hausdorff distance metric has been used in face detection and recognition with good results. It defines the distance metric based only on the geometric similarity between two sets or points. However, not only the geometry but also the local patterns around the points are available in most cases. In this paper a new Hausdorff distance measure is proposed that makes hybrid use of the similarity of the geometry and the local patterns around the points. Several experiments shows that the new method outperforms the conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.1
• /
• pp.32-38
• /
• 1993

In this paper a effective classification method for character recognition is proposed. The existing classification methods select candidates by comparing an unknown input character, with all the standard patterns based on the similarity measur. The proposed method, however, groups similiar characters together and uses their average distance as representative value of the group. We divided the character region into several sub-region and applied ISODATA algorithm to partial vectors of each sub-region to anstruct appropriate number of groups. After computing the distance between partial feature vector and its mapping group, we could collect all the information of input character ultimately. The proposed method showed improvement in the processing speed and certainty in classification than the existing methods.