• Journal of Computing Science and Engineering
• /
• 제11권1호
• /
• pp.24-31
• /
• 2017

Face-based video retrieval has become an active and important branch of intelligent video analysis. Face profiling and matching is a fundamental step and is crucial to the effectiveness of video retrieval. Although many algorithms have been developed for processing static face images, their effectiveness in face-based video retrieval is still unknown, simply because videos have different resolutions, faces vary in scale, and different lighting conditions and angles are used. In this paper, we combined content-based and semantic-based image analysis techniques, and systematically evaluated four mainstream local features to represent face images in the video retrieval task: Harris operators, SIFT and SURF descriptors, and eigenfaces. Results of ten independent runs of 10-fold cross-validation on datasets consisting of TED (Technology Entertainment Design) talk videos showed the effectiveness of our approach, where the SIFT descriptors achieved an average F-score of 0.725 in video retrieval and thus were the most effective, while the SURF descriptors were computed in 0.3 seconds per image on average and were the most efficient in most cases.

• 통합자연과학논문집
• /
• 제3권1호
• /
• pp.43-48
• /
• 2010

본 논문은 지역 부분영상을 이용한 실시간 CCTV결합 시스템에 고나한 연구로써 프레임에 관한 결합 인식방법을 제안한다. 제안된 알고리즘은 기존에 비해 결합속도를 줄이고 이에 따라 전체적인 인식률을 높이는 것을 목표로 하고 있다. 기존 방법인 SIFT알고리즘은 특허가 있고 처리속도가 늦기 때문에 본 논문에서 개선된 지역영상 재생성 방식을 이용하여 실질적으로 CCTV 처리속도에 맞추어 속도를 높였다. 논문은 지역화 이미지를 이용하여 인식률과 속도를 바탕으로 전체적인 시스템 구현과 함께 알고리즘을 소개하는 것으로 구성되어 있으며 실제 실험을 통한 성능을 비교 평가 하였다. 실시간으로 동작하는 CCTV에 적용시킴으로 각각의 화면이 아닌 Inline System으로 감시자의 신체적 피로를 줄이고 경제적인 효과를 볼 수 있고 일반 사용자들도 쉽게 사용할 수 있는 저비용 시스템을 구축하였다.

• 한국지구과학회지
• /
• 제35권5호
• /
• pp.299-304
• /
• 2014

In this study, fossil liverwort (Hepaticae) of Thallites yabei (Kryshtofovich) Harris is described based on the newly obtained material from the Lower Cretaceous Nakdong Formation of Sindong Group, Korea. The thalli of T. yabei is ribbon-like, bifurcating at least three or four times, and has a distinct midrib. Although the thalloid plants are herbaceous with little hard part, the thalli of T. yabei is relatively well preserved to show the sequentially bifurcating pattern in the specimens occurred in the same fossil locality. Such characteristics indicate that they were probably buried in situ. The abundant occurrence of thalli plants also indicate that land was covered densely by them as one of the terrestrial land plant members, and flourished under the tall arbor trees in the humid environment during the Early Cretaceous in the Gyeongsang Basin.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.243-244
• /
• 2007

다양한 디지털 컨텐츠를 검색하기 위해 다양한 디스크립터(Descriptor)가 제안되어 왔다. 그 중 특징점을 기반으로 하는 디스크립터를 이용하여 원본 영상과 기하학적 변형을 포함하는 다양한 변형 영상을 서로 정확하게 정합시키기 위해서는 각 영상에서 동일한 위치에 동일한 개수의 특징점이 추출되는 것이 유리하다. 본 논문에서는 널리 사용되고 있는 해리스(Harris) 특징점 추출 방법을 기반으로 국부 최대값과 정렬을 이용하여 원하는 개수의 특징점을 선택하는 방법을 제안한다.

• KIEE International Transaction on Systems and Control
• /
• 제12D권1호
• /
• pp.7-11
• /
• 2002

In this study, fur the shape-based image retrieval, a method using local differential invariants is proposed. This method calculates the differential invariant feature vector at every feature point extracted by Harris comer point detector. Then through vector quantization using LBG algorithm, all feature vectors are represented by a codebook index. All images are indexed by the histogram of codebook index, and by comparing the histograms the similarity between images is obtained. The proposed method is compared with the existing method by performing experiments for image database including various 1100 trademarks.

• 정보처리학회논문지B
• /
• 제10B권1호
• /
• pp.73-80
• /
• 2003

본 논문에서는 기준영상과 탐색영상 사이의 대응되는 특징 점을 정합 하는 알고리즘을 제안한다. 두 영상에서 특징 점을 찾기 위하여 Harris의 코너 점 검출기를 사용하였다. 기준영상의 각 특징 점에 대해, 정규상관계수가 임계치 이상인 탐색영상의 특징 점들로 후보 정합 점을 구한다. 최종적으로 동적 프로그래밍을 사용하여 후보 정합 점들 중에서 대응되는 특징 점을 구한다. 실험으로 인위적인 영상과 실제 영상에서 특징 점을 정합 하는 결과를 보였다.

• 영미문화
• /
• 제9권1호
• /
• pp.71-90
• /
• 2009

David Harris argues that mass media suppress counter-hegemonic factors in order to reach audience. According to Harris's theory, the success of the film "Tess" depends on its effective adaptation from Thomas Hardy's novel Tess of the D'Urbervilles (1891). Tess (1979), directed by Roman Polansky, casting Nastassia Kinski for Tess, was acclaimed as a professional and commercial success, awarded with various prizes. Hardy's aim at criticizing Victorian English social and moral standard through Tess appears obscure in Polansky's film which focuses on the aesthetics of human body and capital. Polanski's Tess with urban white beauty does not emerge victimized by poverty, which the late twentieth century audience under the capitalist umbrella may abhor. To examine his use of music, sound effect, visual images by means of camera operation—angles, distances, close-ups and frequent movements—light and color, and mythic elements in the film, show Polansky's sharp perception of his contemporary audience's desire and conscientious work upon it.

• 대한족부족관절학회지
• /
• 제28권3호
• /
• pp.111-113
• /
• 2024

Tillaux fractures, a rare type corresponding to Salter-Harris type 3, are observed in approximately 3% of pediatric ankle fractures. They are known to occur primarily via a supination-external rotation mechanism. Maisonneuve fractures, on the other hand, are proximal fibula fractures involving injury on syndesmosis, deltoid ligament, or medial malleolus fracture, occurring via a pronation-external rotation mechanism. These two types of fractures occur through different mechanisms of injury. In this study, a nine-year-old female pediatric patient presented to the outpatient department with ankle pain following a fall from a trampoline and was diagnosed with concurrent Tillaux-like fracture and Maisonneuve fractures. Surgical treatment was performed, resulting in successful recovery.

• 대한수학회논문집
• /
• 제12권4호
• /
• pp.1033-1038
• /
• 1997

A functional central limit theorem for a class of nonlinear stationary Markov processes which are geometrically Harris ergodic is derived.

• 한국지능시스템학회논문지
• /
• 제3권1호
• /
• pp.41-64
• /
• 1993