• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1373-1374
• /
• 2015

본 논문은 복잡한 비선형 모델링 방법인 다항식 기반 RBF 뉴럴 네트워크(Radial Basis Function Neural Network)와 벡터공간에서 임의의 비선형 경계를 찾아 두 개의 집합을 분류하는 방법으로 주어진 조건하에서 수학적으로 최적의 해를 찾는 SVM(Support Vector Machine)를 사용하여 3차원 얼굴인식 모델을 설계하고 두 모델의 3차원 얼굴 인식률을 비교한다. 3D스캐너를 통해 3차원 얼굴형상을 획득하고 획득한 영상을 전처리 과정에서 포인트 클라우드 정합과 포즈보상을 수행한다. 포즈보상 통해 정면으로 재배치한 영상을 Multiple Point Signature기법을 이용하여 얼굴의 깊이 데이터를 추출한다. 추출된 깊이 데이터를 RBFNN과 SVM의 입력패턴과 출력으로 선정하여 모델을 설계한다. 각 모델의 효율적인 학습을 위해 PCA 알고리즘을 이용하여 고차원의 패턴을 축소하여 모델을 설계하고 인식 성능을 비교 및 확인한다.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.372-378
• /
• 2003

Limitations on the linear discriminant analysis (LDA) for face rerognition, such as the loss of generalization and the computational infeasibility, are addressed and illustrated for a small number of samples. The principal component analysis (PCA) followed by the LDA mapping may be an alternative that ran overcome these limitations. We also show that any schemes based on either mappings or template matching are vulnerable to image variations due to rotation, translation, facial expressions, or local illumination conditions. This entails the importance of a proper preprocessing that can compensate for such variations. A simple template matching, when combined with the geometrically correlated feature-based detection as a preprocessing, is shown to outperform mapping techniques in terms of both the accuracy and the robustness to image variations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.10B
• /
• pp.1210-1215
• /
• 2011

In this paper, a supervised adaptive equalization algorithm based on probability density function (PDF) matching method is introduced and its decision-feedback version is proposed for underwater communication channels with strong impulsive noise and severe multipath characteristics. The conventional least mean square (LMS) algorithm based on mean squared error (MSE) criterion has shown to be incapable of coping with impulsive noise and multipath effects commonly shown in underwater communications. The linear PDF matching algorithm, which shows immunity to impulsive noise, however, has revealed to yield unsatisfying performance under severe multipath environments with impulsive noise. On the other hand, the proposed nonlinear PDF matching algorithm with decision feedback proves in the simulation to possess superior robustness against impulsive noise and multipath characteristics of underwater communication channels.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.10
• /
• pp.2112-2122
• /
• 1997

This paper presents a new video codec which is based on 2-D triangular mesh-based motion compensation and two step grid point motion estimation. With this approach the efficiency of compression and the quality of reconstructed images are improved. The compensation of motion for each triangular patch is performed by image warping using motion vectors at the grid points. The prediction error coding and the rate control meet MPEG-4 VM 3.0 specification. The experimental results show that the codec system proposed is simple in complexity and moreover, the quality of decoded images is improved.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.12-18
• /
• 2006

This paper presents a method to extract a good high-resolution image from a low-resolution video in an automatic manner. Since a high-resolution image reconstruction method utilizing several low-resolution input images works better than a conventional interpolation method utilizing single low-resolution input image only if the input images are well registered onto a common high-resolution grid, low-resolution input images should be carefully chosen so that the registration errors can be carefully considered. In this paper, the statistics obtained from the motion-compensated low-resolution images are utilized to evaluate the feasibility of the input image candidates. Maximum motion-compensation error is estimated from the high-resolution image observation model. U the motion-compensation error of the input image candidate is greater than the estimated maximum motion-compensation error, the input image candidate is discarded. The number of good input image candidates and the statistics of the motion-compensation errors are used to choose final input images. The final input images chosen from the input image selection block are given to the following high-resolution image reconstruction block. It is expected that the proposed method is utilized to extract a good high-resolution image efficiently from a low-resolution video without any user intervention.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.258-268
• /
• 2021

Point cloud content is immersive content that represents real-world objects with three-dimensional (3D) points. In the process of acquiring point cloud data or encoding and decoding point cloud data, the resolution of point cloud content could be degraded. In this paper, we propose a method of progressively enhancing the resolution of sequential point cloud contents through inter-frame registration. To register a point cloud, the iterative closest point (ICP) algorithm is commonly used. Existing ICP algorithms can transform rigid bodies, but there is a disadvantage that transformation is not possible for non-rigid bodies having motion vectors in different directions locally, such as point cloud content. We overcome the limitations of the existing ICP-based method by registering regions with motion vectors in different directions locally between the point cloud content of the current frame and the previous frame. In this manner, the resolution of the point cloud content with geometric movement is enhanced through the process of registering points between frames. We provide four different point cloud content that has been enhanced with our method in the experiment.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.37 no.8
• /
• pp.24-32
• /
• 2000

In this paper, we have designed and fabricated a new type power divider to be efficient to a size and electrical performance by folding each quarter-wavelength 70.7 Ω section into a tightly-coupled "meander-line" and inserting a slit. In this type, because of coupling, the electrical phase of quarter -wavelength line and the performance change. For this reason, with the inductive slit and the tuning of quarter-wavelength line length, we have compensated for those. The inductance value of the inserted slit is decided by its width and depth, therefore, we could improve the electrical performance through optimization of inductance. Input and output return losses of the designed power divider were -34.2 dB, -34.3 dB respectively, and isolation was -36.7 dB at 1.75 GHz. Besides, a new design approach reduced occupied substrate area by 3:1 approximately.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1663-1670
• /
• 2014

Recently, lots of research works have been actively focused on the DVC (Distributed Video Coding) techniques which provide a theoretical basis for the implementation of light video encoder. However, most of these studies have showed poorer performances than the conventional standard video coding schemes such as MPEG-1/2, MPEG-4, H.264 etc. In order to overcome the performance limits of the conventional approaches, several channel-divided distributed video coding schemes have been designed in such a way that some information are obtained while generating side information at decoder side and then these are provided to the encoder side, resulting in channel-divided video coding scheme. In this paper, the interpolation scheme by weighted sum of multiple motion-compensated interpolation frames is introduced and a new channel-divided DVC scheme is designed to effectively describe noisy channels based on the motion vector and its matching characteristics. Through several simulations, it is shown that the proposed method performs better than the conventional methods at low bit-rate and keeps the reconstructed visual quality constantly.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.5
• /
• pp.331-339
• /
• 2016

This paper suggests an estimation method of the source signal and the channel impulse response (CIR) using ray-based blind deconvolution (RBD) in the underwater acoustic channel environment where Doppler effect exists by the relative motion between source and receiver. It is difficult to estimate the CIR on Doppler effect by the matched filter with a highly Doppler-sensitive waveform such as the m-sequence signal because Doppler shift can severely degrade the correlation between the received signal corrupted by Doppler effect and the original source signal. In this study, the Doppler-shifted source-signal's phase is estimated using the RBD, and the received signal is compensated by it to obtain the Doppler-corrected CIR. It is verified that using the matched filter with the received signal from the experimental data fails to estimate the CIR while the obtained CIR by the suggested method has the similarity to the propagation path of the ray model. Also, the results show that the reconstructed source signal using the RBD has the better Doppler shift compensation than the Doppler-shifted source signal derived from scattering function.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7A
• /
• pp.676-682
• /
• 2002

In this paper, an effective stereo image compression and reconstruction technique using a new adaptively compensated-disparity prediction scheme is proposed. That is, by adaptively predicting the mutual correlation between the stereo image using the proposed method, the bandwidth of the stereo input image can be compressed to the level of the conventional 2D image and the predicted image also can be effectively reconstructed using this transmitted reference image and disparity data in the receiver. Especially, in the proposed method, once the feature values are extracted from the input stereo image, then the matching window size for the predicted image reconstruction is adaptively selected in accordance with the magnitude of this feature values. From this adaptive disparity estimation method, reduction of the mismatching probability of the disparity vectors is expected and as a result, the image quality in the reconstructed image can be improved. In addition, from some experiments using the CCETT's stereo images of 'Fichier', 'Manege' and 'Tunnel', it is shown that the proposed method improves the PSNR of the reconstructed image to about 9.08 dB on average by comparing with that of the conventional methods. And also, it is found that there is almost no difference between the original image and the predicted image reconstructed through the proposed method by comparison to that of the conventional methods.