• Journal of the Optical Society of Korea
• /
• 제17권5호
• /
• pp.410-414
• /
• 2013

In this paper, we propose a 3D display method combining a pickup process using axially recorded multiple images and an integral imaging display process. First, we extract the color and depth information of 3D objects for displaying 3D images from axially recorded multiple 2D images. Next, using the extracted depth map and color images, elemental images are computationally synthesized based on a ray mapping model between 3D space and an elemental image plane. Finally, we display 3D images optically by an integral imaging system with a lenslet array. To show the usefulness of the proposed system, we carry out optical experiments for 3D objects and present the experimental results.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.17-20
• /
• 2000

This paper describes a shape-based object recognition algorithm using multiple distance images. For the images containing dense edge points and noise, previous Hausdorff distance (HD) measures yield a high ms error for object position and many false matchings for recognition. Extended version of HD measure considering edge position and orientation simultaneously is proposed for accurate matching. Multiple distance images are used to calculate proposed matching measure efficiently. Results are presented for visual images and infrared images.

• 한국생물공학회:학술대회논문집
• /
• 한국생물공학회 2003년도 생물공학의 동향(XIII)
• /
• pp.746-749
• /
• 2003

Alignment of 2D-gel images of biological samples can visualize the difference of expression profiles and also inform us candidates of protein spots to be further analyzed. However, comparison of two proteome images between case and control does not always successfully identify differentially expressed proteins due to sample-to-sample variation. Because of poor reproducibility of 2D-gel electrophoresis, sample-by-sample variations and inconsistent electrophoresis conditions, multiple number of 2D-gel image must be processed to align each other to visualize the difference of expression profiles and to deduce the protein spots differentially expressed with reliability. Alignment of multiple 2D-Gel images and their clustering were carried out by applying various algorithms and statistical methods. In order to align multiple images, multiresolution-multilevel algorithm was found out to be suitable for fast alignment and for distorted images. Clustering of 12 different images implementing a k-means algorithm gives a phylogenetic tree of distance map of the proteomes. Microsoft Visual C++ was used to implement the algorithms in this work.

• 한국컴퓨터정보학회논문지
• /
• 제5권2호
• /
• pp.22-29
• /
• 2000

본 논문은 복합 영상을 위한 내용기반 영상 검색의 효율을 극대화하기 위한 방법을 제안하였다. 영상 검색을 효율적으로 수행하기 위해서는 영상 검색의 후보를 축소와 함께 최적의 특징을 선택하는 것이 필요하다 한가지 영상 특징 패턴에 기반 한 검색 시스템으로는 다양한 종류의 복합 영상에 대한 검색과정에서 영상 도메인이 변화할 경우 검색 효과를 극대화할 수가 없다. 본 논문에서는 검색 영상 도메인이 변하면 질의 영상 특성에 따라 최적의 특징 패턴을 시스템 스스로 선택하는 적응적 자가 특징 선택 기법 통하여 복합 영상의 검색 효율을 극대화하였다. 제안된 방안에서는 검색 효율을 개별적인 특징들에 비해 3% 향상시킬 수 있었으며 다중 SOFM신경망을 통하여 검색 후보를 축소하였다

• Journal of the Optical Society of Korea
• /
• 제14권2호
• /
• pp.109-120
• /
• 2010

We have developed mathematically precise image-processing algorithms for extracting rectilinear images from fisheye images as well as digital pan/tilt/zoom technology. Using this technology, vertical lines always appear as vertical lines in the panned and/or tilted images. Furthermore, polygonal panoramic images composed of multiple rectilinear images have been obtained using the developed digital pan/tilt technology.

• 대한원격탐사학회지
• /
• 제27권1호
• /
• pp.51-58
• /
• 2011

원격탐사 위성 영상의 발전으로 인해 위성에서 취득된 영상을 이용하여 DEM을 제작하는 연구가 계속 진행되고 있다. 본 논문에서는 2개 이상의 Kompsat-2 영상을 이용하여 이를 이용하여 DEM을 제작한다. DEM의 제작에 앞서 궤도-자세각 모델과 RFM 모델을 사용하여 두 장의 영상과 다중 영상에 센서모델을 수립한 경우 3차원 위치결정 정확도 비교를 수행하였다. 또한 수립된 센서모델을 이용하여 객체공간 기반의 영상정합을 수행하였으며, 제작된 DEM을 통해 사용된 영상의 개수에 따른 분석 및 센서 모델별 정확도를 판단했다. 수행결과 다중영상을 사용하여 센서모델을 한 경우 더 높은 위치 정확도가 나왔음을 확인할 수 있었다. 또한 다중영상을 사용하여 제작된 DEM이 스테레오영상을 사용한 것 보다 더 높은 정확도를 가지며, 육안으로 판단할 경우에도 큰 오차들이 줄어 더 좋은 결과를 보여줌을 확인할 수 있었다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제21권2호
• /
• pp.63-73
• /
• 2017

Segmenting the image into multiple regions is at the core of image processing. Many segmentation formulations of an images with multiple regions have been suggested over the years. We consider segmentation algorithm based on the multi-phase level set method in this work. Proposed method gives the best result upon other methods found in the references. Moreover it can segment images with intensity inhomogeneity and have multiple junction. We extend our method (GLIF) in [T. Dultuya, and M. Kang, Segmentation with shape prior using global and local image fitting energy, J.KSIAM Vol.18, No.3, 225-244, 2014.] using a multiphase level set formulation to segment images with multiple regions and junction. We test our method on different images and compare the method to other existing methods.

• 전기학회논문지P
• /
• 제55권4호
• /
• pp.167-175
• /
• 2006

This paper presents a method to segment semiconductor wafer ID on poor quality images. The method is based on multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not so good and hence, we can not control the image quality, target image to be inspected presents poor quality ID and it is not easy to identify and then recognize the ID characters. Conventional several method to segment the interesting ID regions fails on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To find out the optimal solution of multiple template model in ID regions, we introduce newly-developed snake algorithm. Experimental results using images from real FA environment are presented.

• 한국정보처리학회논문지
• /
• 제7권6호
• /
• pp.1834-1843
• /
• 2000

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.225-226
• /
• 2010

The problem in orthoimage generation is to recover occlusion areas. In this study, occlusion areas - double mapping regions of the building roofs - were mutually corrected by using multiple images. The proposed method could be efficient for generating true orthoimages in urban areas.