• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2017-2024
• /
• 1997

The main focus of this paper is the recognition of printed Hangul documents in terms of typeface, character size and character slope for IICS(Intelligent Image Communication System). The fixed-size blocks extracted from documents are analyzed in frequency domain for the typeface classification. The vertical pixel counts and projection profile of bounding box are used for the character size classification and the character slope classification, respectively. The MLP with variable hidden nodes and error back-propagation algorithm is used as typeface classifier, and Mahalanobis distance is used to classify the character size and slope. The experimental results demonstrated the usefulness of proposed system with the mean rate of 95.19% in typeface classification. 97.34% in character size classification, and 89.09% in character slope classification.

• Science of Emotion and Sensibility
• /
• v.1 no.1
• /
• pp.33-40
• /
• 1998

본 논문은 얼굴인식 분야에 있어서 필수 과정인 얼굴 및 얼굴의 주요소인 눈과 입의 추출에 관한 방법을 제시한다. 얼굴 영역 추출은 복잡한 배경하에서 움직임 정보나 색상정보를 사용하지 않고 통계적인 모델에 기반한 일종의 형찬정합 방법을 사용하였다. 통계적인 모델은 입력된 얼굴 영상들의 Hotelling변환 과정에서 생성되는 고유 얼굴로, 복잡한 얼굴 영상을 몇 개의 주성분 갑으로 나타낼 수 있게 한다. 얼굴의 크기, 영상의 명암, 얼굴의 위치에 무관하게 얼굴을 추출하기 위해서, 단계적인 크기를 가지는 탐색 윈도우를 이용하여 영상을 검색하고 영상 강화 기법을 적용한 후, 영상을 고유얼굴 공간으로 투영하고 복원하는 과정을 통해 얼굴을 추출한다. 얼굴 요소의 추출은 각 요소별 특성을 고려한 엣지 추출과 이진화에 따른 프로젝션 히스토그램 분석에 의하여 눈과 입의 경계영역을 추출한다. 얼굴 영상에 관련된 윤곽선 추출에 관한 기존의 연구에서 주로 기하학적인 모양을 갖는 눈과 입의 경우에는 주로 가변 템플릿(Deformable Template)방법을 사용하여 특징을 추출하고, 비교적 다양한 모양을 갖는 눈썹, 얼굴 윤곽선 추출에는 스네이크(Snakes: Active Contour Model)를 이용하는 연구들이 이루어지고 있는데, 본 논문에서는 이러한 기존의 연구와는 달리 스네이크를 이용하여 적절한 파라미터의 선택과 에너지함수를 정의하여 눈과 입의 윤곽선 추출을 실험하였다. 복잡한 배경하에서 얼굴 영역의 추출, 추출된 얼굴 영역에서 눈과 입의 영역 추출 및 윤곽선 추출이 비교적 좋은 결과를 보이고 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.1
• /
• pp.117-121
• /
• 2009

The fisheye image acquired with a fisheye camera has wider field of view than a general use camera. But large distortion of the object in the image requires conversion of the fisheye image to the perspective image because of user's difficult perception. The existing Ishii's method[1] has the problem that the object can has sire and geometrical distortion in the transformed image because it uses equidistance projection. This paper presented a conversion technique of the fisheye image to the perspective image using sealing function. In the experiments, it was shown that our method reduced size and geometrical distortion by applying the scaling function.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.4C
• /
• pp.472-484
• /
• 2004

We proposed 3D mesh watermarking algorithm using CEGI distribution. In the proposed algorithm, we divide a 3D mesh of VRML data into 6 patches using distance measure and embed the same watermark bits into the normal vector direction of meshes that mapped into the cells of each patch that have the large magnitude of complex weight of CEGI. The watermark can be extracted based on the known center point of each patch and order information of cell. In an attacked model by affine transformation, we accomplish the realignment process before the extraction of the watermark. Experiment results exhibited the proposed algorithm is robust by extracting watermark bit for geometrical and topological deformed models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.410-412
• /
• 2021

This paper proposes an improved pedestrian detection method using object and background histograms. Objects detected through the HOG & SVM algorithm are detected in a square shape. Inside the square area, the background and the object area are mixed. If only the area of the object excluding the background is detected, various object-related information may be easily obtained. The size of the detected rectangle is readjusted using an xy-axis projection algorithm to fit the size of the object. And then, the improved object is detected by dividing the background and the object based on the histogram of the object in the readjusted square. The average values of precision and recall, which are reliability evaluations comparing the detected object with the original object, are 97.9% and 90%, respectively.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.1
• /
• pp.36-46
• /
• 2013

The Geostationary Ocean Color Imager (GOCI), the first geostationary ocean color observation instrument launched in 2010 on board the Communication, Ocean, and Meteorological Satellite (COMS), has been generating the operational level 1 data. This study describes a methodology for creating the GOCI true color image and data processing software, namely the GOCI RGB maker. The algorithm uses a generic atmospheric correction and reprojection technique to produce the color composite image. Especially, the program is designed for educational purpose in a way that the region of interest and image size can be determined by the user. By distributing software to public, it would maximize the understanding and utilizing the GOCI data. Moreover, images produced from the geostationary observations are expected to be an excellent tool for monitoring environmental changes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1445-1450
• /
• 2020

Recently, a hologram-like system to provide a realistic experience has been serviced in performances, exhibitions, education. The constructing method for the hologram-like system can be configured in various forms such as a pyramid-typed, a semi-transparent large screen form. However, in various types of hologram-like systems, it is difficult to provide adjustment by changing and revising the content according to the configured hardware characteristics. In this paper, we propose a novel technique that can automatically visualize virtual contents running on heterogeneous hologram-like systems. To change the content to a given hardware configuration, we receive pre-built simple text-based configuration data, and correcting process was performed. According to the results of this paper, we found automatically and easily corrected visualization with the given configuration of the hologram-like system. Also, the problem of reducing the time by manual control in various types of heterogeneous hologram systems was solved.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.3
• /
• pp.305-315
• /
• 1986

Redesign of the mounting system to minimize vibration of a variable displacement engine through computer simulation is considered. A three degree of freedom model is established for an in-line four-cylinder automobile engine with a three point mounting system. The engine mount locations and angles, and isolator sizes are chosen as design parameters. Constraints on isolator deformations and design parameters are imposed. The gradient projection method is utilized for optimization. Simulation studies show significant vibration reduction can be obtained especially at idling speed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.381-385
• /
• 2003

We suggest a method which reduces the search space of a model-base on multiple-view approach for polyhedral object recognition using the ART-1 neural network. In this approach, the model-base is consisted of extracted features from two-dimensional projections observed at the predetermined viewpoints of a viewing sphere enclosing the object.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.656-666
• /
• 1995

본 논문에서는 물체위로 투사된 line stripe으로부터 물체의 표면 정보를 추출하기 위해 2-D Grip paper를 이용해 캘리브레이션하는 방법이 제안되었다. 카메라의 이미지평면과 카메라의 가시범위에 있는 3차원 실세계간의 Projective Tranformation과정에서는 목표물과 이미지 평면사이의 거리나 각도 등이 정보를 실제로 측정해서 알고 있어야만 카메라와 실세계간의 캘리브레이션을 수행할 수 있다. 그러나 이미 크기나 거리를 알고 있는 Grid paper를 이용하면 카메라의 파라미터들에 대한 추정이나 카메라와 실세계간의 측정을 하지 않고서도 목표물위로 투사된 line stripe에 대한 정보를 얻을 수 있고 이를 이용해 물체의 표면에 대한 정보를 얻을 수 있다. 이미 지평면에 투영된 격자패턴에서 구한 교차점들의 위치를 이용해 실제 위치를 찾아낸다. 실제로 레이져스캐너를 이용해 물체위로 line stripe을 투사한 후, 위에서 제시한 방법을 통해 3차원 정보를 구하는 실험결과는 양호하였다.