• 한국통신학회논문지
• /
• 제28권11C호
• /
• pp.1140-1151
• /
• 2003

본 논문에서는 변형 Otsu 이진화 방법과 Hu 모멘트를 기반으로 밝기, 명암도, 크기, 회전, 위치 변화에 강인한 얼굴 인식 방법을 제안한다. 제안하는 변형 Otsu 이진화 방법은 기존의 Otsu 이진화 방법으로부터 또 다른 문턱치 값을 결정하고 이로부터 얻어진 이진 얼굴 영상 2개를 사용함으로써 이진 영상 하나보다 고차원의 특징벡터를 추출할 수 있고, 기존의 Otsu 이진화 방법과 마찬가지로 밝기 및 명암도 변화에 강인한 속성을 가지고 있다. 특징 값으로는 Hu 모멘트를 사용함으로써 크기, 회전, 위치 변화에 강인한 특성을 추가로 가지고 있다 기존의 주요 성분 분석(Principal Component Analysis, PCA) 방법과 제안한 방법을 비교 실험한 결과, 위에서 언급한 5가지 다양한 환경 변화에 대하여 PCA 방법의 평균 인식률은 olivetti Research Laboratory (ORL) 데이터베이스와 AR 데이터베이스에 대해서 각각 68.4%와 51.2%이고, 제안한 방법의 평균 인식률은 각각 93.2%와 81.4%로서 제안한 방법의 인식 성능이 우수함을 확인하였다.

• Spatial Information Research
• /
• 제15권4호
• /
• pp.385-395
• /
• 2007

컴퓨터의 사용과 인터넷이 발달로 인해 데이터의 사용과 공유가 매우 증가하고 있으며, 그에 따라 불법적인 데이터의 보급도 발생하고 있다. 본 연구에서는 이러한 불법적인 데이터의 복제 문제를 해결하기 위해 디지털 워터마킹 기법을 제안한다. 특히, GIS에서 많이 사용하고 있는 데이터인 벡터데이터에 워터마크를 삽입하고, 소유권을 주장할 수 있는 워터마킹 방법을 제안한다. 연구에서 제안한 방법은 벡터데이터의 좌표에 이진 연산을 이용하여 워터마크를 직접 삽입을 하고, 워터마크를 삽입하는 역과정을 통해 워터마크를 추출하는 것이다. 실험 결과를 통해 제안한 방법이 벡터데이터에 대한 다양한 공격에 대해 강인함을 알 수 있었다.

• The Plant Pathology Journal
• /
• 제22권4호
• /
• pp.386-390
• /
• 2006

Extensive research of the Potato virus X(PVX) has been performed in in vitro transcription system using the bacteriophage T7 promoter. We constructed an efficient T-DNA based binary vector, pSNU1, and modified vectors carrying PVX replicons. The suitability of the construct to transiently express PVX RNA using Agrobacterium tumefaciens was tested by analysis of infectivity in plants. The expressed PVX RNA was infectous and systemically spread in three plant species including Nicotiana benthamiana, N. tabacum cv. Xanthi-nc, and Capsicum annuum cv. Chilsungcho. The PVX full length construct, pSPVXp31, was caused severe mosaic symptoms on N. benthamiana, severe necrotic lesions on C. annuum while milder symptoms and delayed mosaic symptoms were appeared on the systemic leaves on N. tabaccum. RT-PCR analysis confirmed the presence of PVX RNAs on both inoculated and systemic leaves in all three plant species tested. Our results indicated that PVX replicons were efficiently expressed PVX RNA in at least three tested species. Further investigation win be needed to elucidate the mechanism of PVX replication, translation, movement and assembly/disassembly processes.

• 대한기계학회논문집B
• /
• 제32권11호
• /
• pp.863-869
• /
• 2008

This paper investigated the new calibration algorithm of a straight-type five-hole pressure probe for measuring three-dimensional flow velocity components. This new calibration algorithm was used for velocity data reduction from the calibration map and based on the combination of a look-up, a binary search algorithm and a geometry transformation including the translation and reflection of nodes in a calibration map. The calibration map was expanded up to the application angle, ${\pm}55^{\circ}$ of a probe. This velocity data reduction method showed a perfect performance without any kind of interpolating errors in calculating yaw and pitch angles from the calibration map. Moreover, when it was applied to an actual flow field including a swirling flow, a good result came out on the whole.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 춘계종합학술대회
• /
• pp.185-191
• /
• 1999

Mathematical morphology based on set theory has been applied to various areas in image processing. Pitas proposed a object recognition algorithm using Morphological Shape Decomposition(MSD), and a new representation scheme called Morphological Shape Representation(MSR). The Pitas's algorithm is a simple and adequate approach to recognize objects that are rotated 45 degree-units with respect to the model object. However, this recognition scheme fails in case of random rotation. This disadvantage may be compensated by defining small angle increments. However, this solution may greatly increase computational complexity because the smaller the step makes more number of rotations to be necessary. In this paper, we propose a new method for object recognition based on MSD. The first step of our method decomposes a binary shape into a union of simple binary shapes, and then a new tree structure is constructed which ran represent the relations of binary shapes in an object. finally, we obtain the feature informations invariant to the rotation, translation, and scaling from the tree and calculate matching scores using efficient matching measure. Because our method does not need to rotate the object to be tested, it could be more efficient than Pitas's one. MSR has an intricate structure so that it might be difficult to calculate matching scores even for a little complex object. But our tree has simpler structure than MSR, and easier to calculated the matchng score. We experimented 20 test images scaled, rotated, and translated versions of five kinds of automobile images. The simulation result using octagonal structure elements shows 95% correct recognition rate. The experimental results using approximated circular structure elements are examined. Also, the effect of noise on MSR scheme is considered.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2006년도 춘계종합학술대회
• /
• pp.943-946
• /
• 2006

XML(Extensible Markup Language)은 운영환경에 독립적인 문서형식을 정의할 수 있다는 장점으로 인해 많은 사용자층을 확보하여 현재 가장 널리 쓰이는 문서형식 중의 하나가 되었다. 그러나 이러한 XML이 모바일 분야와 같이 제한된 메모리와 빠른 전승속도를 요구하는 환경에서도 쓰이게 됨에 따라 파일의 용량과 전송속도에 대한 문제점이 새롭게 대두되고 있다. 이에 XML의 바이너리화에 대한 논의가 진행되고 있으며, XML의 구조를 유지하여 기존의 장점을 최대한 살리면서 문서 크기를 줄일 수 있는 방안으로 XML 정보셋을 이용한 Fast Infoset 방식이 주목을 받고 있다. 이에 본 논문에서는 XML을 바이너리화하기 위하여 Fast Infoset 방식 및 ASN.1(Abstract Syntax Notation One)의 인코딩 방법 중 하나인 PER(Packed Encoding Rules)을 이용하여 모듈을 설계하였으며, XML 문서가 바이너리 XML 문서로 인코딩되는 과정을 단계적으로 확인할 수 있는 인터페이스로 인코더를 구현하였다.

• International Journal of Contents
• /
• 제14권1호
• /
• pp.1-6
• /
• 2018

Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.

• 한국항공운항학회지
• /
• 제19권4호
• /
• pp.44-50
• /
• 2011

This paper presents the algorithm for attitude determination of an aircraft using binary image. An image feature vector, which is invariant to translation, scale and rotation, is constructed to capture the functional relations between the feature vector and the corresponding aircraft attitude. An iterated least squares method is suggested for estimating the attitude of given aircraft using the constructed feature vector library. Simulation results show that the proposed algorithm yields good estimates of aircraft attitude in most viewing range, although a relatively large error occurs in some limited viewing direction.

• 대한기계학회논문집A
• /
• 제30권5호
• /
• pp.488-495
• /
• 2006

The demand for the use of 3D CAD data over the Internet environment has been increased. However, transmission of 3D CAD data has delayed the communication effectiveness because of the CAD data size. Lightweight CAD file design methodology is required for rapid transmission in the distributed environment. In this paper, to derive lightweight CAD files from commercial CAD systems, a file translation system producing a native file is constructed first by using the InterOp and API of the ACIS kernel. Using the B-rep model and mesh data extracted from the native file, the lightweight CAD file with topological information is constructed as a binary file. Since the lightweight CAD file retains topological information, it is applied to the dimensional verification, digital mock-ups and visualization of CAD files. Effectiveness of the proposed lightweight CAD file is confirmed through various case studies.

• 동력기계공학회지
• /
• 제12권4호
• /
• pp.18-25
• /
• 2008

This paper investigated the new calibration algorithm of a straight-type five-hole pressure probe necessary for calculating three-dimensional flow velocity components. The new data reduction method Includes a look-up, a geometry transformation such as the translation and reflection of nodes, and a binary search algorithm. This new calibration map was applied up to the application angle, ${\pm}55^{\circ}$ of a probe. As a result, this data reduction method showed a perfect performance without any kind of interpolation errors In calculating yaw and pitch angle from the calibration map.