• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.425-433
• /
• 2018

In this paper, we propose a super-resolution reconstruction algorithm for plenoptic images based on the reliability of disparity. The subperture image generated by the Flanoptic camera image is used for disparity estimation and reconstruction of super-resolution image based on TV_L1 algorithm. In particular, the proposed image reconstruction method is effective in the boundary region where disparity may be relatively inaccurate. The determination of reliability of disparity vector is based on the upper, lower, left and right positional relationship of the sub-aperture image. In our method, the unreliable vectors are excluded in reconstruction. The performance of the proposed method was evaluated by comparing to a bicubic interpolation method, a conventional disparity based method and dictionary based method. The experimental results show that the proposed method provides the best performance in terms of PSNR(Peak Signal to noise ratio), SSIM(Structural Similarity).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.12
• /
• pp.756-763
• /
• 2014

In this paper, we introduce a new sparse signal recovery algorithm referred to as the matching pursuit with greedy tree search (GTMP). The tree search in our proposed method is implemented to minimize the cost function to improve the recovery performance of sparse signals. In addition, a pruning strategy is employed to each node of the tree for efficient implementation. In our performance guarantee analysis, we provide the condition that ensures the exact identification of the nonzero locations. Through empirical simulations, we show that GTMP is effective for sparse signal reconstruction and outperforms conventional sparse recovery algorithms.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.21-28
• /
• 2016

Compressed sensing is a signal processing technique for efficiently acquiring and reconstructing in an under-sampled (i.e., under Nyquist rate) representation. Specially, a block compressed sensing with Smoothed Projected Landweber (BCS-SPL) framework is one of the most widely used schemes. Currently, a variety of BCS-SPL schemes have been actively studied. However, when restoring, block sizes have effects on the reconstructed visual qualities, and in this paper, both a basic scheme of BCS-SPL and several modified schemes of BCS-SPL with structured measurement matrix are analyzed for the effects of the block sizes on the performances of reconstructed image qualities. Through several experiments, it is shown that a basic scheme of BCS-SPL provides superior performance in block size 4.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.226-234
• /
• 2016

Electrical resistance tomography (ERT) is an imaging technique where the internal resistivity distribution inside an object is reconstructed. The ERT image reconstruction is a highly nonlinear ill-posed problem, so regularization methods are used to achieve desired image. The reconstruction outcome is dependent on the type of regularization method employed such as l2-norm, l1-norm, and total variation regularization method. That is, use of an appropriate regularization method considering the flow characteristics is necessary to attain good reconstruction performance. Therefore, in this paper, regularization methods are tested through numerical simulations with different flow conditions and the performance is compared.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.45-52
• /
• 2018

A single-image super-resolution is a process of restoring a high-resolution image from a low-resolution image. Recently, the super-resolution using the deep neural network has shown good results. In this paper, we propose a neural network structure that improves speed and performance over conventional neural network based super-resolution methods. To do this, we analyze the conventional neural network based super-resolution methods and propose solutions. The proposed method reduce the 5 stages of the conventional method to 3 stages. Then we have studied the optimal width and depth by experimenting on the width and depth of the network. Experimental results have shown that the proposed method improves the disadvantages of the conventional methods. The proposed neural network structure showed superior performance and speed than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1682-1687
• /
• 2020

We study the problem of sampling a subset of nodes of graphs for bandlimited graph signals such that the signal values on the sampled nodes provide the most information in order to reconstruct the original graph signal. Instead of directly minimizing the reconstruction error, we focus on minimizing the upper bound of the reconstruction error to reduce the complexity of the selection process. We further simplify the upper bound by applying useful approximations to propose a low-weight greedy selection process that is iteratively conducted to find a suboptimal sampling set. Through the extensive experiments for various graphs, we inspect the performance of the proposed algorithm by comparing with different sampling set selection methods and show that the proposed technique runs fast while preserving a competitive reconstruction performance, yielding a practical solution to real-time applications.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.137-140
• /
• 2000

카메라의 렌즈 등 광학장비의 성능 제한으로 인하여 초점이 맞지 않아 흐려지고 잡음으로 훼손된 영상을 복원하는데 일반적으로 반복복원방법이 사용된다. 이 경우에 가속변수는 훼손영상에 관계없이 영상전체에 일률적으로 적용되기 때문에 흐려짐 훼손이 심한 윤곽부분도 훼손이 작은 평면영역이 같이 일정하게 처리되어 수렴속도가 느려지고 시각적으로 중요한 윤곽부분의 복원에는 효율적이지 못하다. 이러한 문제점을 해결하기 위하여 본 논문에서는 흐려짐 훼손이 작은 평면영역은 가속변수를 작게하고 훼손이 큰 윤곽영역은 가속변수를 크게 하여 영상의 국부적인 특성에 따라 적응적으로 반복 복원하는 방법을 제안하였다. 제안한 복원방법은 기존의 방법과 비교하여 수렴속도가 빨라지고 시각적으로 중요한 윤곽정보의 복원에도 효율적임을 실험결과를 통해 할 수 있었으며, MSE면에서도 우수하였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.54-59
• /
• 2019

본 논문은 대화 시스템인 챗봇의 성능 향상을 위한 생략 복원 기술의 정확률을 올리기 위한 유효 발화문 인식 모델을 제안한다. 생략 복원 기술은 챗봇 사용자의 현재 발화문의 생략된 정보를 이전 발화문으로부터 복원하는 기술이다. 유효 발화문 인식 모델은 현재 발화문의 생략된 정보를 보유한 이전 발화문을 인식하는 역할을 수행한다. 유효 발화문 인식 모델은 BERT 기반 이진 분류 모델이며, 사용된 BERT 모델은 한국어 문서를 기반으로 새로 학습된 한국어 사전 학습 BERT 모델이다. 사용자의 현재 발화문과 이전 발화문들의 토큰 임베딩을 한국어 BERT를 통해 얻고, CNN 모델을 이용하여 각 토큰의 지역적인 정보를 추출해서 발화문 쌍의 표현 정보를 구해 해당 이전 발화문에 생략된 개체값이 있는지를 판단한다. 제안한 모델의 효과를 검증하기 위해 유효 발화문 인식 모델에서 유효하다고 판단한 이전 발화문만을 생략 복원 모델에 적용한 결과, 생략 복원 모델의 정확률이 약 5% 정도 상승한 것을 확인하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.4
• /
• pp.537-545
• /
• 2013

The elastic recovery of a metal seal is a factor that can be used to assess its sealing performance. In this study, a compliant mechanism topology optimization has been performed to find a structure of a metal O-ring seal that can maintain excellent sealing performance with a maximized elastic recovery over extended operation. An evolutionary structural optimization (ESO) was used as a topology optimization algorithm with two different types of objective functions considering both flexibility and stiffness. In particular, a circular design domain was adopted to consider the outer shape of the metal O-ring seal. The elastic recovery of the optimal topology was calculated and compared to that of a commercial product.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.339-345
• /
• 2013

In this paper, the probabilistic exclusion based orthogonal matching pursuit (PEOMP) algorithm for the sparse signal reconstruction is proposed. Some of recent greedy algorithms such as CoSaMP, gOMP, BAOMP improved the reconstruction performance by deleting unsuitable atoms at each iteration. They still often fail to converge to the solution because the support set could not escape from a local minimum. PEOMP helps to escape by excluding a random atom in the support set according to a well-chosen probability function. Experimental results show that PEOMP outperforms several OMP based algorithms and the $l_1$ optimization method in terms of exact reconstruction probability.