• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.37-39
• /
• 2016

최근 Convolutional neural networks(CNN) 기반의 초해상화 기법인 Super-Resolution Convolutional Neural Networks (SRCNN) 이 좋은 PSNR 성능을 발휘하는 것으로 보고되었다 [1]. 하지만 많은 제안 방법들이 고주파 성분을 복원하는데 한계를 드러내는 것처럼, SRCNN 도 고주파 성분 복원에 한계점을 지니고 있다. 또한 SRCNN 의 네트워크 층을 깊게 만들면 좋은 PSNR 성능을 발휘하는 것으로 널리 알려져 있지만, 네트워크의 층을 깊게 하는 것은 네트워크 파라미터 학습을 어렵게 하는 경향이 있다. 네트워크의 층을 깊게 할 경우, gradient 값이 아래(역방향) 층으로 갈수록 발산하거나 0 으로 수렴하여, 네트워크 파라미터 학습이 제대로 되지 않는 현상이 발생하기 때문이다. 따라서 본 논문에서는 네트워크 층을 깊게 하는 대신에, 입력을 다중 채널로 구성하여, 네트워크에 고주파 성분에 관한 추가적인 정보를 주는 방법을 제안하였다. 많은 초해상화 기법들이 고주파 성분의 복원 능력이 부족하다는 점에 착안하여, 우리는 네트워크가 고주파 성분에 관한 많은 정보를 필요로 한다는 것을 가정하였다. 따라서 우리는 네트워크의 입력을 고주파 성분이 여러 가지 강도로 입력되도록 저해상도 입력 영상들을 구성하였다. 또한 잔차신호 네트워크(residual networks)를 도입하여, 네트워크 파라미터를 학습할 때 고주파 성분의 복원에 집중할 수 있도록 하였다. 본 논문의 효율성을 검증하기 위하여 set5 데이터와 set14 데이터에 관하여 실험을 진행하였고, SRCNN 과 비교하여 set5 데이터에서는 2, 3, 4 배에 관하여 각각 평균 0.29, 0.35, 0.17dB 의 PSNR 성능 향상이 있었으며, set14 데이터에서는 3 배의 관하여 평균 0.20dB 의 PSNR 성능 향상이 있었다.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.220-223
• /
• 2020

초해상화란, 저해상도의 영상으로부터 고해상도 영상을 복원하는 이미지 처리 기법이다. 최근 영상 출력 장치의 발전으로 고해상도의 영상을 출력할 장치는 많아지는 한편, 이에 맞는 고해상도 영상을 찍을 영상 기록 장치의 보급은 이에 비해 부족한 실정이다. 따라서 저해상도의 영상을 고해상도 영상으로 변환하는 초해상화 연구는 많은 분야에서 활용되고 있다. 문화재 영상에서의 초해상화는 특히 기존 문화재의 질감, 무늬 등을 보존해야하기 때문에 정교한 초해상화 과정이 요구된다. 본 논문에서는 문화재 영상의 초해상화 과정에 집중해, 기존 문화재의 질감, 무늬 등을 잘 보존하면서 영상 데이터의 양이 상대적으로 적은 경우에도 활용 가능한 기계학습 기범, GLM-SI를 이용한 문화재 영상 초해상화 방법을 제안한다. GLM-SI 를 사용한 초해상화 결과, 문화재 영상에서 선행 방법인 SI 에 비하여 4 배 초해상화에서 PSNR 0.12dB, SSIM 0.017, 8 배 초해상화에서 PSNR 0.23dB, 0.033 의 성능적 향상을 얻을 수 있었다.

• Journal of Digital Policy
• /
• v.3 no.1
• /
• pp.27-32
• /
• 2024

In this paper, proposes a super resolution method that enhances the quality of results by refining texture features, contrasting each, and utilizing the results as weights. For the improvement of quality, a precise and clear restoration result in details such as boundary areas is crucial in super resolution, along with minimizing unnecessary artifacts like noise. The proposed method constructs a residual block structure with multiple paths and skip-connections for feature estimation in conventional Convolutional Neural Network (CNN)-based super resolution methods to enhance quality. Additional learning is performed for sharpened and blurred image results for further texture analysis. By contrasting each super resolution result and allocating weights through this process, the proposed method achieves improved quality in detailed and smoothed areas of the image. The experimental results of the proposed method, evaluated using the PSNR and SSIM values as quality metrics, show higher results compared to existing algorithms, confirming the enhancement in quality.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.303-306
• /
• 2021

이미지 초해상도는 영상 취득 과정에서 센서와 렌즈의 물리적인 한계 등으로 인하여 의해 화질이 저하된 이미지를 더 높은 배율로 복원하는 문제이다. 이미지 초해상도는 딥러닝을 통해 놀라운 성능향상을 이루었지만, 카메라로 촬영된 실제 이미지에서는 좋은 성능을 내지 못하였다. 이는 딥러닝에서는 'bicubic' 커널로 down-sampling된 합성 이미지 데이터를 사용하였던 것과 달리 실제 이미지에서는 'bicubic' 커널을 통한 화질 저하와는 다른 화질 저하, 즉 다른 커널을 통한 화질 저하가 발생하기 때문이다. 따라서 실제 이미지에 대한 성능을 높이기 위해서는 이에 대한 정확한 커널 예측이 필요하다. 최근 주목받기 시작한 이미지 초해상도를 위한 커널 예측은 초해상도를 잘 시켜주는 커널을 직접 찾는 방법[10, 13]과 이미지의 분포와 커널을 통해 다운샘플된 이미지에 대한 분포를 일치시켜주면서 커널을 예측하는 방법[14]으로 나누어져 있다. 그러나 두 방법 모두 ill-posed problem 인 커널 예측 문제를 한 장의 이미지만으로 해결하려는 것이기 때문에 정확한 예측에는 어려움이 발생한다. 따라서 본 논문에서는 두 장의 이미지를 활용한 이미지 화질 저하 커널 예측 방법을 제안한다. 제안된 방법은 두 장의 이미지가 같은 카메라를 통해 촬영되었으며 이때 이미지 화질 저하는 카메라에 의해서만 영향을 받는다는 가정을 기반으로 한다. 즉, 두 장의 이미지는 같은 커널을 통해 저하된 이미지라는 가정을 한다. 제안된 방법은 [14]에서처럼 이미지 분포를 기반으로 한 커널 예측을 진행하며, 이미지 초해상도를 진행하고자 하는 이미지 외에 참고 이미지 또한 같은 커널에서 화질 저하를 시켰을 때 본래의 이미지와 같은 분포에 있도록 학습을 진행한다. 결과적으로 본 논문에서는 두 장의 이미지를 사용하였을 때 더욱 정확하게 커널을 찾을 수 있음을 보여준다. 두 장의 이미지를 활용하는 방식이 한 장의 이미지만을 활용하는 기존의 최고 수준의 방법에 비해 합성된 다양한 커널 데이터셋[14]에서 약 0.17dB 성능 향상이 있었다.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.2
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.54-63
• /
• 2011

This paper proposes a fast learning-based interpolation algorithm to up-scale an input low-resolution image into a high-resolution image. In conventional learning-based super-resolution, a certain relationship between low-resolution and high-resolution images is learned from various training images and a specific high frequency synthesis information is derived. And then, an arbitrary low resolution image can be super-resolved using the high frequency synthesis information. However, such super-resolution algorithms require heavy memory space to store huge synthesis information as well as significant computation due to two-dimensional matching process. In order to mitigate this problem, this paper presents one-dimensional patch-based learning and synthesis. So, we can noticeably reduce memory cost and computational complexity. Simulation results show that the proposed algorithm provides higher PSNR and SSIM of about 0.7dB and 0.01 on average, respectively than conventional bicubic interpolation algorithm.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.