• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• 한국전자파학회논문지
• /
• 제11권7호
• /
• pp.1121-1127
• /
• 2000

PCB에서의 불요전자파 복사를 줄이기 위하여 많은 방법들이 이용되고 있으나, 본 논문에서는 영상평면을 적용하여 불요 전자파 복사를 줄이는 방법을 제시하였다. PCB에서의 영상평면 효과를 해석하기 위한 모델을 제시하였으며, FEM(Finite Element Method)으로 시뮬레이션을 한 후, 전계 프로브를 사용하여 불요 전자파의 세기를 측정하였다. 그 결과 PCB에서 복사되는 불요전자파의 세기는 영상평면의 폭과 간격에 따라 다르게 나타나며 측정한 결과와 시뮬레이션 결과가 유사한 것을 알 수 있었다. 그러므로 PCB에서 복사되는 불요전자파를 억제하기 위하여 영상평면을 적절히 사용한다면 EMI 저감 대책면에서 효과적이라는 것을 알 수 있었다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1992년도 추계학술대회
• /
• pp.22-25
• /
• 1992

화학적 이동성을 이용하여, 생체의 경우 지방질의 영상 혹은 물성분의 영상을 얻을 수 있다. 여러 가지 기술을 사용하여 분리된 성분의 자기공명 영상을 얻었다. Dixon의 방법은 두 번의 영상실험을 하여 지방질 영상과 물성분 영상을 구분할 수 있으며, 부분적 자기장의 불균질성에 영향을 적게 받고 다층 영상법에 용이하게 적용할 수 있다. CHESS와 SECSI 방법은 한번의 영상실험으로 물 또는 지방질 영상을 획득할 수 있다. 그러나 부분적 자기장의 불균질성에 영향을 많이 받으며, 다층영상법에 적용하기에는 어려운 점이 있다. 화학 성분의, 즉 지방질과 물성분의 분리의 척도가 되는 지방질 신호대 물성분신호 비에 있어 SECSI 방법이 가장 우수함을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.554-557
• /
• 2002

In this paper, PDP driving circuit is designed to show the pattern of still-image with ADS (Address Display Separation) driving method. The designed circuits consist of three stages which are the image processing program, digital logic parts, and power circuits. The Image processing program is designed serial-communication with RS-232C using BASIC language. Digital logic parts design ADS driving signals with Xilinx FPGA and are simulated by ModelSim 5.5f. Power circuits convert output of digital logic parts into high voltage which panel is drived.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제26권3호
• /
• pp.156-184
• /
• 2022

In this article, we propose a novel variational model for restoring color images corrupted by mixed multiplicative Gamma noise and additive Gaussian noise. The model involves a data-fidelity term that characterizes the mixed noise as an infimal convolution of two noise distributions and the saturation-value total variation (SVTV) regularization. The data-fidelity term facilitates suitable separation of the multiplicative Gamma and Gaussian noise components, promoting simultaneous elimination of the mixed noise. Furthermore, the SVTV regularization enables adequate denoising of homogeneous regions, while maintaining edges and details and diminishing the color artifacts induced by noise. To solve the proposed nonconvex model, we exploit an alternating minimization approach, and then the alternating direction method of multipliers is adopted for solving subproblems. This contributes to an efficient iterative algorithm. The experimental results demonstrate the superior performance of the proposed model compared to other existing or related models, with regard to visual inspection and image quality measurements.

• 한국인터넷방송통신학회논문지
• /
• 제14권3호
• /
• pp.155-162
• /
• 2014

본 논문에서는 이동차량 양상 안정화를 위한 효율적인 흔들림 보정 기법을 제안한다. 제안된 흔들림 보정 기법은 입력으로 받은 영상 이미지 프레임의 색상 분리를 통한 변환 및 분리정보에 대한 누적 히스토그램을 계산하였고, 흔들리는 차량용 영상 이미지를 보정한 결과에서 색상 정보를 맞추기 위해 히스토그램 매칭을 하였다. 본 논문에서 제안된 흔들림 보정 기법은 기존 차량 영상 안정화 기술과 비교하였을 때, 휘도 및 컬러 레벨의 비교를 통해 노이즈가 가장 적고 영상의 자연스러움이 더 뛰어난 복원 결과를 얻을 수 있었다. 또한, 흔들림 보정 기법은 메모리를 사용하지 않고 실시간으로 처리를 통해 다른 방법과 비교하여 효율성을 입증하였다.

• 한국분무공학회지
• /
• 제2권2호
• /
• pp.16-23
• /
• 1997

In this research a novel two-reference-beam double pulse holographic technique for the measurments of particle sizes and velocities was developed. This holographic method features the capability of separation of the first and second particle images by using two reference beams instead of one and the change of the polarization direction of laser light. The developed holographic system was tested through the measurements of droplet sizes and velocities in the spray created by two high speed impinging jets. The overall spray pattern clearly revealed the inherent wave nature. Smaller and faster droplets were generated with larger impingement angle, higher jet velocity. and smaller orifice diameter.

• Journal of Magnetics
• /
• 제16권4호
• /
• pp.444-448
• /
• 2011

In the present study, we separated the marker particles from the suspending particle mixture solution using isotacho-electrophoresis technique, a novel quantitative ionic particle separation method, in the microchannel. A multiple stacking zone of the suspending particle was visualized with variations in electric field strength, pH value and concentration of the ionic solution. In particular, the electrophoretic mobility of ionic particle (fluorescein) was estimated based on the electrophoretic velocity value measured by the particle image velocimetry. As a result, isotacho-electrophoresis zones were clearly visualized as going downstream in the electric field. The particle migration velocity increased proportional to the applied voltage increase; it was also affected by the pH value variations in the ionic solution.

• 대한산업공학회지
• /
• 제17권2호
• /
• pp.27-37
• /
• 1991

A recognition algorithm for Hangul is developed by structural analysis to Hangul in this theses. Four major procedures are proposed : preprocessing, type classification, separation of consonant and vowel, recognition. In the preprocessing procedure, the thinning algorithm proposed by CHEN & HSU is applied. In the type classification procedure, thinned Hangul image is classified into one of six formal types. In the separation of consonant and vowel procedure, starting from branch-points which are existed in a vowel, character elements are separated by means of tracing branch-point pixel by pixel and comparison with proposed templates. In the same time, the vowels are recognized. In the recognition procedure, consonants are extracted from the separated Hangul character and recognized by modified Crossing method. Recognized characters are converted into KS-5601-1989 codes. The experiments show that correct recognition rate is about 80%-90% and recognition speed is about 2-3 character persecond in three types of different input data on computer with 80386 microprocessor.

• 한국운동역학회지
• /
• 제13권1호
• /
• pp.23-38
• /
• 2003

The purpose of this study is to develop an improved marker auto-identification algorithm for reduce of data processing time through improve the efficiency of noise elimination and marker separation. The maker auto-identification algorithm was programming named KUMAS used Delphi language. For the study, various experiments were conducted for the verification of KUMAS. and compared two systems of established with the KUMAS. Four different motions - cycling, gait, rotation, and pendulum -, were selected and tested. Motions were filmed 30Hz frames rate per second. ${\chi}^2$ used for statistical analysis. Significant level were ${\alpha}=.05$. The test results were as follow. 1. Increased the success ratio of marker auto-identification. 2. The efficiency of marker auto-identification was remarkably improved through marker separation, noise elimination. 3. The marker auto-identification ability was improved in 2D-image plane include the 3D motion. 4. Significant different were found between KUMAS and B-SYS(established system) with non-input the artificial noise frames, input the artificial noise frames and total frames.