• 방송공학회논문지
• /
• 제13권3호
• /
• pp.380-387
• /
• 2008

본 논문에서는 음성 특성에 기반을 둔 보컬 영역 검색 알고리듬을 적용하는 가라오케 시스템을 제시한다. 제안한 시스템에서 입력 음악은 보컬 영역 검색 알고리듬을 통해 보컬 부분과 반주 부분으로 분류된다. 그런 다음, 보컬 영역에 대해서만 보컬 제거기법을 적용한다. 보컬 영역 검색에서는 TICFT (twice iterated composite Fourier transform) 영역에서 보컬의 특성을 고려하여 분류를 수행한다. 보컬 제거를 위해서 대역 통과 필터링 된 보컬 영역으로부터 보컬 성분을 추출하고, 이를 원래의 음악에서 감산함으로써 보컬 성분이 제거된 음악을 얻는다. 본 논문에서 제시한 기법은 4곡의 노래에 적용하고, 그 성능을 평가한다.

• ETRI Journal
• /
• 제43권1호
• /
• pp.109-119
• /
• 2021

Self-recovery is a tamper-detection and image recovery methods based on data hiding. It generates two types of data and embeds them into the original image: authentication data for tamper detection and reference data for image recovery. In this paper, a region-based scalable self-recovery (RSS) method is proposed for salient-object images. As the images consist of two main regions, the region of interest (ROI) and the region of non-interest (RONI), the proposed method is aimed at achieving higher reconstruction quality for the ROI. Moreover, tamper tolerability is improved by using scalable recovery. In the RSS method, separate reference data are generated for the ROI and RONI. Initially, two compressed bitstreams at different rates are generated using the embedded zero-block coding source encoder. Subsequently, each bitstream is divided into several parts, which are protected through various redundancy rates, using the Reed-Solomon channel encoder. The proposed method is tested on 10 000 salient-object images from the MSRA database. The results show that the RSS method, compared to related methods, improves reconstruction quality and tamper tolerability by approximately 30% and 15%, respectively.

• 가정과삶의질연구
• /
• 제23권1호
• /
• pp.53-63
• /
• 2005

Purpose of this study was to examine economic contributions to regional economic of home-based family businesses. Results showed that home-based family businesses create additional employments within the region, contribute to taxation of the regional economy, and improve regional financing. In addition, home-based family businesses do contribute to regional economy through consuming goods and services within the region and providing goods and services to the region. Through analyzing economic contributions to regional economy of home-based family businesses, it can be suggested that strong support for the home-based family businesses is needed for growth of the regional economy.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.418-422
• /
• 2009

Generally, algorithms for generating disparity maps can be clssified into two categories: region-based method and feature-based method. The main focus of this research is to generate a disparity map with an accuracy depth information for 3-dimensional reconstructing. Basically, the region-based method and the feature-based method are simultaneously included in the proposed algorithm, so that the existing problems including false matching and occlusion can be effectively solved. As a region-based method, regions of false matching are extracted by the proposed MMAD(Modified Mean of Absolute Differences) algorithm which is a modification of the existing MAD(Mean of Absolute Differences) algorithm. As a feature-based method, the proposed method eliminates false matching errors by calculating the vector with SIFT and compensates the occluded regions by using a pair of adjacent SIFT matching points, so that the errors are reduced and the disparity map becomes more accurate.

• 전자공학회논문지SC
• /
• 제42권5호
• /
• pp.51-58
• /
• 2005

본 논문에서는 유방 초음파 볼륨영상에서 진단하고자 하는 종양 영역을 율왜곡 기반(rate-distortion based) 시드영역 확장 법으로 분할하는 알고리듬을 제안한다. 제안된 분할법에서는 율은 윤곽의 거친 정도를 나타내고 왜곡은 영역의 동질성 정도를 나타내는데, 흉부 종양 볼륨으로부터 획득한 2차원 단면 영상에서 설정된 초기 시드영역에서 시작하여 이러한 율과 왜곡을 동시에 최소화하는 주위영역 중 하나씩 시드영역으로 병합한다. 이러한 병합은 시드영역의 윤곽 화소당 평균 율왜곡 비용이 최대가 될 때까지 반복적으로 수행한다. 이렇게 함으로써 최종 시드영역은 동질성이 잘 유지되고 부드러운 윤곽을 갖게 된다. 마지막으로 모든 단면 영상에 있는 최종 시드영역의 윤곽들을 이용하여 3차원 흉부 종양을 추출한다. 실험 결과, 제안한 방법이 초음파 데이터에 대하여 평균 에러율이 약 4% 미만으로 나타났다.

• 수산경영론집
• /
• 제46권1호
• /
• pp.1-13
• /
• 2015

This study is aimed comparative analysis for business performance of land-based ezo abalone (Haliotis discus hannai) seed farms by standardizing cost structures by region and farming size. The result of survey on average farming incomes by region showed that farming incomes in Haenam and Jindo regions were much higher than those in other regions. Followed by Wando region, incomes in other regions were analyzed to be relatively lower. It is shown that farming incomes became higher as farm size increased. Farming incomes per unit size which were modified from farming incomes by region were highest in Jindo region, followed by East sea region, Wando and Haenam regions. Incomes in Jeju and Yeosu regions were analyzed to be relatively lower. Results on farming incomes per unit size ($m^2$) showed that both farming incomes and profits became higher as size increased. It implies that a scale effectiveness might exist in case of land-based abalone culture system. Impacts of major factors on farming profits and returns on investment in abalone seed aquaculture are summarized as follow. First, only if the survival rate increased by 10% with improvement of component ratio, variable effects became largest. In variable effects of other factors, a variation in Jindo region was largest and on the other hand, a variation in Yeosu region was shown to be smallest.

• 한국산학기술학회논문지
• /
• 제6권5호
• /
• pp.367-372
• /
• 2005

본 논문은 가변 영역을 이용한 내용기반 영상 검색 방법을 제안한다. 내용기반 검색에서 색상을 이용하는 경우 대부분 컬러 히스토그램을 사용한다. 그러나 기존 컬러 히스토그램 검색 방법들은 양자화 오류 등의 이유로 정확성이 떨어지고, 공간정보가 부족한 단점이 있다. 이를 극복하기 위해 제안 방법은 색상 정보를 HSV 공간으로 변환하여 순수 색상 정보인 hue 성분만을 양자화하여 히스토그램을 구한다. 한편 공간정보가 부족한 문제점을 해결하기 위해 색상 특징과 영역간의 상관관계를 고려하여 객체 영역을 선정한다. 선정된 객체 영역에서는 영역 크기를 유지한다. 그러나 비객체 영역은 한 개의 영역으로 통합된다. 가변적인 영역이 선정된 후 색상 특징을 이용해 검색한다. 실험 결과 제안방법이 정확율(precision) 평균으로 10$\%$ 향상되었다.

• 수산경영론집
• /
• 제54권3호
• /
• pp.45-67
• /
• 2023

The purpose of this study is to construct a regional-sector-fishery-offshore and inshore fishery competitiveness index, examine the types and changes of competitiveness, and derive implications by processing data of the Survey on the Current Status of Offshore and Inshore Fishery from 2013 to 2020 for this study. The main results of this study can be summarized as follows. First, considering the competitiveness of offshore and inshore fishery by region and year, Jeonnam, Jeju, and Incheon were relatively competitive. Second, considering the competitiveness of inshore fishery by region and year, we found that Jeonnam, Chungnam, Jeonbuk, and Jeju were relatively competitive. Third, looking at the types of competitiveness based on the competitiveness index in the management sector of offshore and inshore fisheries by region and year, Ulsan, Jeonnam, and Gyeongbuk were relatively competitive between 2014 and 2020. Fourth, Jeonnam and Jeju were relatively competitive between 2014 and 2020 based on the competitiveness index in the fishing sector of offshore and inshore fisheries by region and year. Fifth, we found that Jeonnam, Jeju, and Chungnam were relatively strong in the competitiveness of offshore and inshore fishery, combining the offshore and inshore fishery indexes by region and year. The results of this study have some limitation on outlier treatment, grade assignment, and weight for aggregation, so research considering these needs to be done in the future. In conclusion, the results of this study which were derived objectively and scientifically in the era of the 4th industrial revolution, when evidence-based decision-making was becoming critical, are expected to help the central or local governments determine the priority of support projects or investments.

• 한국컴퓨터산업학회논문지
• /
• 제2권3호
• /
• pp.265-274
• /
• 2001

본 논문에서는 얼굴의 특징 영역에 근거하여 얼굴을 검색할 수 있는 내용기반의 얼굴 검색 시스템을 제안한다. 질의를 위해 이름이나 주민등록번호와 같은 키워드를 사용하는 대신에, 제안한 시스템은 시각적 질의로서 얼굴 영상을 사용한다. 이를 위해, 얼굴 구성 요소를 포함하는 특징 영역을 HSl 칼라 모델이 제공하는 칼라 정보와 Wavelet 변환이 제공하는 에지 정보를 이용하여 추출한 후, 신경망을 통하여 분류ㆍ검색한다. 제안한 검색 시스템은 Oracle DBMS를 사용하여 클라이언트/서버 환경으로 구축되었다. 150개의 다양한 얼굴 영상으로 실험한 결과, 약 88.3%의 검색율을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.389-392
• /
• 2005

In the maskless photolithography based on the Digital Micromirror Device (DMD) by Texas Instruments Inc. (TI), the micromirror array works as a virtual photomask to write patterns directly onto Flat Panel Display (FPD) at high speed with low cost. However, it is neither simple to generate region-based patterns for the micromirror array nor easy to deliver sequences of patterns for the micromirror controller. Moreover, the quality of lithography yields the precise synchronization between generating sequence of patterns and irradiation rate off micromirrors. In this study, the region-based pattern generating system for maskless photolithography is devised. To verify salient features of devised functionalities, the prototype system is implemented and the system is evaluated with actual DMD based photolithography. The results show that proposed pattern generating method is proper and reliable. Moreover, the devised region-based pattern generating system is robust and precise enough to handle any possible user specified mandate and to achieve the quality of photolithography required by FPD manufacturer.