http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A new approach for content-based video retrieval
Nac-Woo Kim,Byung-Tak Lee,Jai-Sang Koh,Ho-Young Song 한국콘텐츠학회(IJOC) 2008 International Journal of Contents Vol.4 No.2
In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.
A new approach for content-based video retrieval
Kim, Nac-Woo,Lee, Byung-Tak,Koh, Jai-Sang,Song, Ho-Young The Korea Contents Association 2008 International Journal of Contents Vol.4 No.2
In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio-temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.
Chromosomal Polymorphism in Korean Natural Populations of Drosophila immigrans
Kim, Nam-Woo,Lee, Jae-Doo,Lee, Yang-Suk,Joo, Eun-Young,Kim, Jin-Tae,Rim, Nac-Ryong 한국곤충학회 2003 Entomological Research Vol.33 No.1
To analyze chromosome inversions of Drosophila immigrans, wild flies were captured from large vineyards located in the suburbs of Yecheon and Gyeongsan from October 1999 to 2001. With the egg samples obtained singly at each of the 799 females of D. immigrans, cytological examinations were carried out for the type and frequency of inversions. Two types of different inversions were found only in the second chromosome. The inversions detected were known to be the cosmopolitan inversion "A" and "B". The mean frequency of inversion A was estimated to be 0.074 in Yecheon and 0.066 in Gyeongsan and that of B was to be 0.026 in Yecheon and 0.021 in Gyeongsan, respectively. In the frequency ratio, inversion A was significantly higher than that of B. The present populations of D. immigrans showed subtle differences from other Korean populations in inversion frequencies. To account for the local variations observed in inversion frequencies, several hypotheses are discussed such as founding event or selective force.
김낙우(Nac-woo Kim),송호영(Ho-young Song),김봉태(Bong-tae Kim) 한국통신학회 2007 韓國通信學會論文誌 Vol.32 No.10C
본 논문에서는 효과적인 영상 검색을 위한 방법으로서 JSEG 영상 분할 기법을 통한 영역 기반의 영상 인덱싱 및 검색 기법을 제안한다. JSEG은 영상을 색상 분류에 따라 양자화하고 이에 영역 윈도우를 적용시켜 J-image를 만든 다음, 세부 분할된 영역의 성장과 병합을 통하여 영상을 효과적으로 분할하는 방법이다. 제안하는 영상 검색시스템은 JSEG에 의해 분할된 영상을 사용자에게 질의 영상으로 주고, 사용자로 하여금 분할 영상에서 관심 영역군(群)을 선택하게 한다. 그리고 나서, 사용자 질의에 의해 선택된 영역의 MBR을 구하고 이 영역의 중심을 기준으로 다중 윈도우 마스크를 생성하여 적용시킴으로써 특정 관심 영역을 중심으로 한 영상의 전역적인 특징을 추출한다. 최종적으로 추출된 특징의 성능 비교를 위한 기술자로는 누적 히스토그램을 이용하였다. 제안된 방법은 특정 영역에서의 특징과 전역 특징을 동시에 추출하여 검색에 이용함으로써 보다 빠르고 정확하게 사용자가 원하는 영상을 제공할 수 있다. 실험 결과는 영상 색인 및 검색에 있어서 제안된 방법이 영상 기반의 검색 기법과 비교하여 더 효과적임을 보여준다. In this paper, we propose the region-based image retrieval method using JSEG which is a method for unsupervised segmentation of color-texture regions. JSEG is an algorithm that discretizes an image by color classification, makes the J-image by applying a region to window mask, and then segments the image by using a region growing and merging. The segmented image from JSEG is given to a user as the query image, and a user can select a few segmented regions as the query region. After finding the MBR of regions selected by user query and generating the multiple window masks based on the center point of MBR, we extract the feature vectors from selected regions. We use the accumulated histogram as the global descriptor for performance comparison of extracted feature vectors in each method. Our approach fast and accurately supplies the relevant images for the given query, as the feature vectors extracted from specific regions and global regions are simultaneously applied to image retrieval. Experimental evidence suggests that our algorithm outperforms the recent image-based methods for image indexing and retrieval.
김낙우(Nac-Woo Kim),이현용(Hyun-Yong Lee),이준기(Jun-Gi Lee),이병탁(Byung-Tak Lee),이기홍(Ki-Hong Lee) 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
본 논문에서는 전고체 이차전지에서의 전구체 복합물 형성 시 최적 출력 특성을 내는 합성비 결정을 위한 영상 분석 기술을 제안한다. 전고체 배터리의 음극재 및 양극재 SEM(Scanning Electron Microscope) 영상에서 양극 복합물 구조체의 다양한 크기와 형상으로부터 watershed 기반 입도(Granulometry) 및 공극도(Porocity) 분석 기술을 제공함으로써, 활물질과 고체전해질 간 접촉 계면 최대화 및 접촉 저항을 최소화할 수 있는 전고체 이차전지 공정최적화 기술에 적용할 수 있도록 한다. 전구체 복합물의 공극도 수치와 전지 충방전 특성 및 에너지 밀도 간 성능 비교를 통해 최적화된 전구체 복합물 최적합성비를 예측할 수 있다.
김낙우(Nac-Woo Kim),이현용(Hyun-Yong Lee),박상준(Sang-Jun Park),이준기(Jun-Gi Lee),이병탁(Byung-Tak Lee) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
본 논문에서는 convolutional neural network, long-short term memory, one-class support vector machine 등의 개별 모델과 앙상블 모델을 기반으로 테슬라 코일과 플라즈마 구에서 취득된 복합센서데이터에 대한 이상 진단을 실행하고 성능을 비교 분석하였다. 먼저 열화상 데이터를 포함한 복합센싱데이터를 데이터 특징에 따라 개별 모델에 각각 적용하고, weighted model average방식의 앙상블 모델을 통해 최종 이상진단 정확도를 구하였다. 앙상블 모델의 구현 결과는 83.6%의 이상진단 정확도를 나타냈다.