• 한국멀티미디어학회논문지
• /
• 제14권11호
• /
• pp.1392-1400
• /
• 2011

최근 대부분의 디지털 이미지 응용분야에서는 영상 처리 및 분석을 위해 고해상도 이미지나 비디오가 요구되고 있다. 한편, 일반적인 영상획득시스템으로부터 획득한 영상신호는 획득하는 과정에서 물리적 영향, 제조 기술의 한계 및 환경적인 영향 등으로 인하여 영상의 화질 저하를 가져온다. 이러한 문제를 해결하기위해 연구되고 있는 방법 중 하나인 초해상도 복원 기술은 동일한 물체를 촬영한 다수의 저해상도 영상으로 고해상도 영상을 만들어내는 영상복원기술이다. 본 논문에서는 S&A (Shift & Add) 방법에 POCS (Projection onto Convex Sets) 이론을 적용하여 기존의 방법보다 개선된 알고리즘을 제안한다. 기존의 알고리즘은 잡음에 약하다는 문제점이 있다. 이를 해결하기 위해 제안한 방법에서는 복원단계에 사용되는 참조영상을 POCS이론에 적용하여 기존의 S&A방법과 결합하였다. 또한 광학적 왜곡에 해당하는 카메라 블러(blur) 연산자로 주파수 영역에서 BLPF (Butterworth Low-pass Filter)를 사용하여 기존방법의 문제점인 링잉현상을 해결하였다. 실험결과를 통해 잡음에 강하고 영상의 고주파영역을 향상시킨 제안한 초해상도 방법의 우수성을 확인하였고, 객관적 평가를 위해 기존의 방법과 PSNR (peak signal to noise ratio)을 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2109-2123
• /
• 2017

This paper presents a super-resolution reconstruction method based on sparse representation for two-dimensional bar code images. Considering the features of two-dimensional bar code images, Kirsch and LBP (local binary pattern) operators are used to extract the edge gradient and texture features. Feature extraction is constituted based on these two features and additional two second-order derivatives. By joint dictionary learning of the low-resolution and high-resolution image patch pairs, the sparse representation of corresponding patches is the same. In addition, the global constraint is exerted on the initial estimation of high-resolution image which makes the reconstructed result closer to the real one. The experimental results demonstrate the effectiveness of the proposed algorithm for two-dimensional bar code images by comparing with other reconstruction algorithms.

• 전기학회논문지
• /
• 제57권2호
• /
• pp.294-302
• /
• 2008

In this paper, we present a new image up-sampling method which registers low resolution images to the high resolution grid when Bayesian super-resolution image processing is performed. The proposed up-sampling method interpolates high-resolution pixels using high-frequency data lying in all the low resolution images, instead of up-sampling each low resolution image separately. The interpolation is based on B-spline non-uniform re-sampling, adjusted for the super-resolution image processing. The experimental results demonstrate the effects when different up-sampling methods generally used such as zero-padding or bilinear interpolation are applied to the super-resolution image reconstruction. Then, we show that the proposed hybird up-sampling method generates high-resolution images more accurately than conventional methods with quantitative and qualitative assess measures.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.71-76
• /
• 2020

In this paper, we propose a super-resolution method that reconstructs compressed low-resolution images into high-resolution images. We propose a CNN model with a small number of parameters, and even if quantization is applied to the proposed model, super-resolution can be implemented without deteriorating the image quality. To further improve the quality of the compressed low-resolution image, a new degradation model was proposed instead of the existing bicubic degradation model. The proposed degradation model is used only in the training process and can be applied by changing only the parameter values to the original CNN model. In the super-resolution image applying the proposed degradation model, visual artifacts caused by image compression were effectively removed. As a result, our proposed method generates higher PSNR values at compressed images and shows better visual quality, compared to conventional CNN-based SR methods.

• Journal of International Society for Simulation Surgery
• /
• 제1권2호
• /
• pp.57-61
• /
• 2014

We present a robust 3D facial reconstruction method using a single image generated by face-specific super resolution technique. Based on the several consecutive frames with low resolution, we generate a single high resolution image and a three dimensional facial model based on it. To do this, we apply PME method to compute patch similarities for SR after two-phase warping according to facial attributes. Based on the SRI, we extract facial features automatically and reconstruct 3D facial model with basis which selected adaptively according to facial statistical data less than a few seconds. Thereby, we can provide the facial image of various points of view which cannot be given by a single point of view of a camera.

• 한국정보통신학회논문지
• /
• 제22권3호
• /
• pp.425-433
• /
• 2018

본 논문에서는 시차의 신뢰도를 기반으로 플렌옵틱 영상의 초고해상도 복원 알고리즘을 제안한다. 그리고 플렌옵틱 카메라 영상으로부터 생성한 서브어퍼처(sub-aperture) 이미지는 TV_L1알고리즘에 기반한 시차 추정과 초고해상도 영상 복원에 활용된다. 특히 제안된 알고리즘은 시차가 부정확하게 나타날 수 있는 경계 역역에서 향상된 성능을 보인다. 시차 벡터의 신뢰도는 서브어퍼처 이미지의 상하좌우 각 위치별 영역에 따른 분산을 고려하여 판단한다. 신뢰도가 낮은 시차벡터는 초고해상도 영상 복원시 제외된다. 제안된 방법은 바이큐빅 보간 방법과 기존의 시차기반방법 그리고 사전기반 방법과 비교하여 평가되었다. 성능 평가에서 초고해상도 영상복원의 결과는 PSNR, SSIM 관점에서 성능을 비교하여 최상의 성능을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3745-3761
• /
• 2020

Low-rank representation methods already achieve many applications in the image reconstruction. However, for high-gradient image patches with rich texture details and strong edge information, it is difficult to find sufficient similar patches. Existing low-rank representation methods usually destroy image critical details and fail to preserve edge structure. In order to promote the performance, a new representation-based image super-resolution reconstruction method is proposed, which combines gradient domain guided image filter with the structure-constrained low-rank representation so as to enhance image details as well as reveal the intrinsic structure of an input image. Firstly, we extract the gradient domain guided filter of each atom in high resolution dictionary in order to acquire high-frequency prior information. Secondly, this prior information is taken as a structure constraint and introduced into the low-rank representation framework to develop a new model so as to maintain the edges of reconstructed image. Thirdly, the approximate optimal solution of the model is solved through alternating direction method of multipliers. After that, experiments are performed and results show that the proposed algorithm has higher performances than conventional state-of-the-art algorithms in both quantitative and qualitative aspects.

• 한국통신학회논문지
• /
• 제31권8C호
• /
• pp.786-794
• /
• 2006

본 논문에서는 초고해상도 영상을 복원하기 위한 최적화 기법으로 널리 사용되는 PCG(Preconditioned Conjugate Gradient) 기법을 위한 새로운 preconditioner를 제안하였다. 제안된 preconditioner는 기존의 블록 circulant preconditioner를 확장하여 roughness 벌칙 함수에 대해서 효과적인 수렴이 가능하도록 한 것으로써, 잡음에 민감한 기존 방법의 성능을 개선할 수 있는 것이다. 제안된 preconditioner의 성능을 확인하기 위한 실험과 시뮬레이션에서 제안된 PCG 방법은 기존 방법보다 우수한 수렴 속도를 보였다.

• 한국멀티미디어학회논문지
• /
• 제22권11호
• /
• pp.1242-1250
• /
• 2019

Super resolution technique aims to convert a low-resolution image with coarse details to a corresponding high-resolution image with refined details. In the past decades, the performance is greatly improved due to progress of deep learning models. However, universal solution for various objects is a still challenging issue. We observe that learning super resolution with a general dataset has poor performance on faces. In this paper, we propose a super resolution fusion scheme that works well for both general- and face datasets to achieve more universal solution. In addition, object-specific feature extractor is employed for better reconstruction performance. In our experiments, we compare our fusion image and super-resolved images from one- of the state-of-the-art deep learning models trained with DIV2K and FFHQ datasets. Quantitative and qualitative evaluates show that our fusion scheme successfully works well for both datasets. We expect our fusion scheme to be effective on other objects with poor performance and this will lead to universal solutions.

• 대한조선학회논문집
• /
• 제59권2호
• /
• pp.72-79
• /
• 2022

Deep-learning-based Super-Resolution (SR) methods were evaluated to reconstruct pressure fields with a high resolution from low-resolution images taken from a coarse grid simulation. In addition to a canonical SRCNN(super-resolution convolutional neural network) model, two modified models from SRCNN, adding an activation function (ReLU or Sigmoid function) to the output layer, were considered in the present study. High resolution images obtained by three models were more vivid and reliable qualitatively, compared with a conventional super-resolution method of bicubic interpolation. A quantitative comparison of statistical similarity showed that SRCNN model with Sigmoid function achieved best performance with less dependency on original resolution of input images.