• Journal of KIISE:Software and Applications
• /
• v.35 no.10
• /
• pp.616-626
• /
• 2008

The face shape extracted by the depth values has different appearance as the most important facial feature information and the face images decomposed into frequency subband are signified personal features in detail. In this paper, we develop a method for recognizing the range face images by combining the multiple frequency domains for each depth image and depth fusion using fuzzy integral. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area. It is used as the reference point to normalize for orientated facial pose and extract multiple areas by the depth threshold values. In the second step, we adopt as features for the authentication problem the wavelet coefficient extracted from some wavelet subband to use feature information. The third step of approach concerns the application of eigenface and Linear Discriminant Analysis (LDA) method to reduce the dimension and classify. In the last step, the aggregation of the individual classifiers using the fuzzy integral is explained for extracted coefficient at each resolution level. In the experimental results, using the depth threshold value 60 (DT60) show the highest recognition rate among the regions, and the depth fusion method achieves 98.6% recognition rate, incase of fuzzy integral.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1501-1514
• /
• 2008

The face shape extracted by the depth values has different appearance as the most important facial information. The face images decomposed into frequency subband are signified personal features in detail. In this paper, we develop a method for recognizing the range face images by multiple frequency domains for each depth image using the modified fuzzy c-mean algorithm. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area. And the second step takes into consideration of the orientated frontal posture to normalize. Multiple contour line areas which have a different shape for each person are extracted by the depth threshold values from the reference point, nose tip. And then, the frequency component extracted from the wavelet subband can be adopted as feature information for the authentication problems. The third step of approach concerns the application of eigenface to reduce the dimension. And the linear discriminant analysis (LDA) method to improve the classification ability between the similar features is adapted. In the last step, the individual classifiers using the modified fuzzy c-mean method based on the K-NN to initialize the membership degree is explained for extracted coefficient at each resolution level. In the experimental results, using the depth threshold value 60 (DT60) showed the highest recognition rate among the extracted regions, and the proposed classification method achieved 98.3% recognition rate, incase of fuzzy cluster.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2003.05b
• /
• pp.364-365
• /
• 2003

모델에 입력되는 지형자료의 형태는 좌표별 고도가 체계적으로 정리된 DEM(Digital Elevation Model)형태를 사용할 수 있으며, 과거에는 이러한 지형자료를 얻기 위해 대상지역의 지형도 중 등고선을 대상으로 좌표별 고도수치를 정리하여 구축하거나, 섬세한 지형자료를 구축하고자 할 경우 각 고도별 등고선자료를 scan한 후에 각 등고선별 고도자료의 위상관계를 설정해 주는 작업을 진행하였으나, 두 방법 모두 상당량의 수정작업과 반복작업이 요구되는 단점을 갖고 있었다. 그러나 국립지리원 주도로 1998년 9월부터 시작된 NGIS(National Geogralhic Information Sydtem)사업에 의해 구축된 수치지도를 이용하여 등고선별 고도자료를 추출하고, 이를 가공하여 모델의 입력자료로 활용하는 방법이 최근에 소개되고 있으며, 지형자료의 구축에 소요되는 시간 및 정확한 자료를 구축할 수 있다. (중략)

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.2 no.1
• /
• pp.46-53
• /
• 1984

This paper deals with the practical application in the way how the automatic contouring can be done by DTM, the results of investigation confirm that the digital contouring is equivalent to results from direct photogrammetric contouring. The data acquisition is restericted in 841$(29{\times}29)$ regular grid points, the interpolation is done by concepts of finite elements. finally, the output map is relatively compare with A-10 contour maps.

• Journal of the Korea Computer Graphics Society
• /
• v.2 no.1
• /
• pp.68-76
• /
• 1996

One of the major problems in GIS(Geographical Information Systems) involves acquiring 3-D terrain data. Because conventional methods such as land surveying or analysis of aerial photographs are costly, the method of using existing paper maps has been gaining considerable attention. This method demands three processing steps: 1) extraction of contours, 2) assignment of height values to the extracted contours, 3) reconstruction of 3-D terrain data. In this paper we systematically develop a procedure for acquiring 3-D terrain data from contour solutions. For the first two steps, we describe the necessary operations and roughly sketch solutions. For the last step, we propose an efficient raster-based algorithm and present the results of experiments with existing paper map images.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.4
• /
• pp.19-26
• /
• 2005

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.10a
• /
• pp.266-271
• /
• 1998

본 논문에서는 칼라지도영상으로부터 GIS의 벡터링 과정에 사용할 벡터링 영역(도로, 해안선, 등고선 등)을 추출하는 방법에 대해 연구하였다. 입력영상으로는 트루칼라영상을 사용할 경우 추출 영역의 칼라가 비교적 균일하게 분포되지만 데이터량이 방대하여 처리에 어려움이 있어 현실적이지 못하므로 이를 양자화하여 256칼라 영상으로 변환한 후 사용할 수 있도록 하였다. 추출 단계에서는 Lab칼라공간에서 mahalanobis 거리 및 방향성 마스크를 사용하여 다양한 칼라 분포를 흡수할 수 있도록 하여 배경 영역을 배제하면서 연결성이 있는 추출결과를 얻을수 있도록 하였다. 그리고 추출된 결과를 원영상과 중첩해 보면서 기호, 문자 등의 요소로 인해 끊어진 영역이나 추출시 발생되는 피할 수 없는 잡영을 편집하여 제거할 수 있는 기능을 제공하였다. 추출된 결과는 벡터링 작업에 직접 사용 가능한 형태로 추출되도록 하였는데 실제 벡터링 작업에 다양한 추출영역을 사용해 봄으로써 이를 검증하였다.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.239-244
• /
• 1998

ESP(Electronic Speckle Pattern Interferometry) is an optical technique to measure deforamtion of engineering components and materials in industrial areas. ESPI, a non-contact and non-destructive measuring method, is capable of providing full-field results with high spatial resolution and high speed. One of important application aspects using electronic speckle pattern interferometry is to generate contours of a diffuse object in order to provide data for 3-D shape analysis and topography measurement. The electronic speckle contouring is suitable for providing measurement range from millimeters to several centimeters. In this study, we introduce the contouring method by modified dual-beam speckle pattern interferometer and a shift of the two illumination beams through optical fiber in order to obtain the contour fringe patterns. Before the experiments, we performed the geometric analysis for dual-beam-shifted ESPI contouring. And by this geometric analysis, we performed the electronic speckle contouring experiment. We used 4-frame phase shifting method with PZT for quantitative analysis of contour fringes. Finally, we showed good agreements between the geometric analysis and experimental results.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.609-611
• /
• 1998

본 논문에서는 수치고도모델로부터 정확한 등고선을 추출하는 방법을 연구하였다. 이것은 하나의 높이 평면과 DEM 데이터의 교점 테스트를 통하여 등고선을 찾는 방법이다. 정해진 높이 평면과 교차하는 지형의 모든 점을 찾아내므로 등고선을 정확히 찾아낸다는 장점이 있다. 본 논문의 결과를 비교 분석함으로서 연구의 정확성을 도모하였다.

• Korean Journal of Remote Sensing
• /
• v.14 no.2
• /
• pp.129-136
• /
• 1998

This paper deals with a problem encountered in the course of constructing digital elevation model from a contour map. Deficiencies of widely used linear interpolation method is described, and an interpolation method for internal points of a single closed contour is proposed. Control points not on a plane are searched and interpolated. The method is applied to an artificial contour lines and real contour lines. The result shows natural and accurate reconstruction.