• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.19-29
• /
• 2003

This paper presents a novel hybrid classifier for face recognition with artificially generated virtual training samples. We utilize both the nearest neighbor approach in feature angle space and a connectionist model to obtain a synergy effect by combining the results of two heterogeneous classifiers. First, a classifier called the nearest feature angle (NFA), based on angular information, finds the most similar feature to the query from a given training set. Second, a classifier has been developed based on the recall of stored frontal projection of the query feature. It uses a frontal recall network (FRN) that finds the most similar frontal one among the stored frontal feature set. For FRN, we used an ensemble neural network consisting of multiple multiplayer perceptrons (MLPs), each of which is trained independently to enhance generalization capability. Further, both classifiers used the virtual training set generated adaptively, according to the spatial distribution of each person's training samples. Finally, the results of the two classifiers are combined to comprise the best matching class, and a corresponding similarit measure is used to make the final decision. The proposed classifier achieved an average classification rate of 96.33% against a large group of different test sets of images, and its average error rate is 61.5% that of the nearest feature line (NFL) method, and achieves a more robust classification performance.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.18-24
• /
• 2004

SPECT technology is used for the reconstructed image in the field of industry noncontact measurement system. One of the distortion problems in reconstructed image quality is a collimator characterictic. The image distortion is caused by a geometrical structure of the collimator. This paper indicated a correction method to remove the image distortion by the structure of the collimator, and compared with the existing correction method. The correction. method removed the image distortion to use deconvolution of projection data with the shift-variant blurring function in the frequency domain. In this pater, I simulated with the collimator angle and distance between the detector and the center of object. and verified with expeimental data. The validity and limitation of correction method is studied for actual industrial applications.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.397-402
• /
• 2008

본 논문에서는 햅틱 인터랙션 기반의 3차원 가상 얼굴 메이크업 시뮬레이션에서 메이크업 대상에 대한 정교한 페인팅을 적용하기 위한 자동화된 마스크 생성 방법을 개발한다. 본 연구에서는 메이크업 시뮬레이션 이전의 전처리 과정에서 마스크를 생성한다. 우선, 3차원 스캐너 장치로부터 사용자의 얼굴 텍스쳐 이미지와 3차원 기하 표면 모델을 획득한다. 획득된 얼굴 텍스쳐 이미지로부터 AdaBoost 알고리즘, Canny 경계선 검출 방법과 색 모델 변환 방법 등의 영상처리 알고리즘들을 적용하여 마스크 대상이 되는 주요 특정 영역(눈, 입술)들을 결정하고 얼굴 이미지로부터 2차원 마스크 영역을 결정한다. 이렇게 생성된 마스크 영역 이미지는 3차원 표면 기하 모델에 투영되어 최종적인 3차원 특징 영역의 마스크를 레이블링하는데 사용된다. 이러한 전처리 과정을 통하여 결정된 마스크는 햅틱 장치와 스테레오 디스플레이기반의 가상 인터페이스를 통해서 자연스러운 메이크업 시뮬레이션을 수행하는데 사용된다. 본 연구에서 개발한 방법은 사용자에게 전처리 과정에서의 어떠한 개입 없이 자동적으로 메이크업 대상이 되는 마스크 영역을 결정하여 정교하고 손쉬운 메이크업 페인팅 인터페이스를 제공한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.431-434
• /
• 2005

본 논문은 유비쿼터스 컴퓨팅 환경 기반에서의 서명인식 시스템 구현을 기술한다. 구현된 시스템은 PDA와 전자 서명입력기를 이용하여 서명데이터를 획득하고 이 데이터를 유비쿼터스 환경인 무선랜을 이용하여 인증 서버로 전송하여 서버로부터 인증된 결과를 받도록 하였다. 본 시스템의 구성은 터치 스크린을 통한 서명입력이 가능한 PDA와 전자서명입력기를 장착한 무선단말기를 사용하는 클라이언트 부분과 서명을 검증하는 서버 부분으로 나누어 구현 하였다. 본 논문에서 인식알고리즘으로는 서명영상을 구간분할한 후 PCA와 LDA를 사용하여 특징값을 추출한다. 학습과정에서 미리 구한 고유값을 이용하여 서명입력기로부터 획득한 서명데이터를 같은 공간에 투영시켜 서로간의 유사도를 비교하도록 하여 서명인식 속도 및 성능을 개선하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.05a
• /
• pp.45-45
• /
• 2004

B-rep 기반의 솔리드 복원 기법은 비교적 복잡한 물체의 경우에도 복원이 잘 되지만, 후보면의 수가 증가함에 따라 탐색 공간 및 시간이 기하급수적으로 늘어나는 단점이 있다. 빈번한 조합 탐색과 복잡한 기하 연산으로 인해 도면이 복잡해질수록 복원 효율성이 떨어지고, 모호성이 발생하는 문제가 있다. 그러나, 이차 곡면을 포함하는 복잡한 물체에 대해서도 복원이 가능하므로 복원 대상 범위가 넓다고 할 수 있다. CSG 기반의 솔리드 복원 기법은 세 투영면에서 돌출 시킨 각각의 솔리드를 서로 교차시켜서 3차원 물체를 복원하는 방법으로, 복잡한 조합 탐색이나 기하 연산 작업을 하지 않게 때문에 비교적 효율적인 복원이 가능하다.(중략)

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1172-1179
• /
• 2022

This paper describes a design of point scalar multiplier for public-key cryptography based on binary Edwards curves (BEdC). For efficient implementation of point addition (PA) and point doubling (PD) on BEdC, projective coordinate was adopted for finite field arithmetic, and computational performance was improved because only one inversion was involved in point scalar multiplication (PSM). By applying optimizations to hardware design, the storage and arithmetic steps for finite field arithmetic in PA and PD were reduced by approximately 40%. We designed two types of point scalar multipliers for BEdC, Type-I uses one 257-b×257-b binary multiplier and Type-II uses eight 32-b×32-b binary multipliers. Type-II design uses 65% less LUTs compared to Type-I, but it was evaluated that it took about 3.5 times the PSM computation time when operating with 240 MHz. Therefore, the BEdC crypto core of Type-I is suitable for applications requiring high-performance, and Type-II structure is suitable for applications with limited resources.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.9
• /
• pp.114-121
• /
• 2004

Thermal design changes and analysis on the engineering model of Command Telemetry Unit(CTU) for a geostationary communications satellite arc performed for the purpose of developing an engineering qualification model. A thermal model is developed by using power consumption measurement values of each functional board and thermal cycling test results. In modeling heat dissipated EEE parts, heat dissipation is imposed evenly on the EEE part footprint area which is projected to the printed circuit board. All the EEE parts of CTU meet the requirement of their allowable temperature range when placed on the engineering qualification level of thermal vacuum environments in accordance with the proposed thermal design changes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.246-248
• /
• 2022

Binary Edwards curves (BEdC), a new form of elliptic curves proposed by Bernstein, satisfy the complete addition law without exceptions. This paper describes an efficient hardware implementation of point scalar multiplication on BEdC using projective coordinates. Modified Montgomery ladder algorithm was adopted for point scalar multiplication, and binary field arithmetic operations were implemented using 257-bit binary adder, 257-bit binary squarer, and 32-bit binary multiplier. The hardware operation of the BEdC crypto-core was verified using Zynq UltraScale+ MPSoC device. It takes 521,535 clock cycles to compute point scalar multiplication.

• Korean Journal of Optics and Photonics
• /
• v.33 no.6
• /
• pp.310-316
• /
• 2022

In this paper, the difference in modulation transfer function (MTF) results according to the change in the angle of a slant target when measuring a presampled MTF was confirmed, and the difference was reduced by fitting the edge spread function graph obtained to reduce the error by the target's rotation. Due to the feature of the presampled MTF method, the spatial frequency changed due to the sensor's projected intensity being changed by the target's rotation, and it was confirmed that the difference in the MTF value occurred depending on the rotation angle of the target. In this paper, the MTF was calculated after fitting only one column of the acquired image. It was confirmed that the rotation error is smaller compared to the case of the presampled MTF method and this fitting method can be applied to a scene that contains various target angles, such as auto-focusing using the MTF.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1185-1194
• /
• 2015

A spherical panoramic image does not conform to the pin-hole camera model, and, hence, it is not possible to utilize previous techniques consisting of plane-to-plane transformation. In this paper, we propose a new method to estimate the planar geometric transformation between the planar image and a spherical panoramic image. Our proposed method estimates the transformation parameters for latitude, longitude, rotation and scaling factors when the matching pairs between a spherical panoramic image and a planar image are given. A planar image is projected into a spherical panoramic image through two steps of nonlinear coordinate transformations, which makes it difficult to compute the geometric transformation. The advantage of using our method is that we can uncover each of the implicit factors as well as the overall transformation. The experiment results show that our proposed method can achieve estimation errors of around 1% and is not affected by deformation factors, such as the latitude and rotation.