• 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.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.203-212
• /
• 2024

Simultaneous motion is essential in the activities of daily living (ADL). For motion intention recognition, surface electromyogram (sEMG) and corresponding motion label is necessary. However, this process is time-consuming and it may increase the burden of the user. Therefore, we propose a simultaneous motion recognition framework using data augmentation based on muscle activation model. The model consists of multiple point sources to be optimized while the number of point sources and their initial parameters are automatically determined. From the experimental results, it is shown that the framework has generated the data which are similar to the real one. This aspect is quantified with the following two metrics: structural similarity index measure (SSIM) and mean squared error (MSE). Furthermore, with k-nearest neighbor (k-NN) or support vector machine (SVM), the classification accuracy is also enhanced with the proposed framework. From these results, it can be concluded that the generalization property of the training data is enhanced and the classification accuracy is increased accordingly. We expect that this framework reduces the burden of the user from the excessive and time-consuming data acquisition.

• Journal of Biomedical Engineering Research
• /
• v.45 no.3
• /
• pp.118-127
• /
• 2024

Commonly deep learning methods for enhancing the quality of medical images use unpaired dataset due to the impracticality of acquiring paired dataset through commercial imaging system. In this paper, we propose a supervised learning method to enhance the quality of ultrasound images. The U-net model is designed by incorporating a divide-and-conquer approach that divides and processes an image into four parts to overcome data shortage and shorten the learning time. The proposed model is trained using paired dataset consisting of 828 pairs of low-quality and high-quality images with a resolution of 512x512 pixels obtained by varying the number of channels for the same subject. Out of a total of 828 pairs of images, 684 pairs are used as the training dataset, while the remaining 144 pairs served as the test dataset. In the test results, the average Mean Squared Error (MSE) was reduced from 87.6884 in the low-quality images to 45.5108 in the restored images. Additionally, the average Peak Signal-to-Noise Ratio (PSNR) was improved from 28.7550 to 31.8063, and the average Structural Similarity Index (SSIM) was increased from 0.4755 to 0.8511, demonstrating significant enhancements in image quality.

• Current Optics and Photonics
• /
• v.8 no.2
• /
• pp.127-137
• /
• 2024

The distribution of tags is an important factor that affects the performance of radio-frequency identification (RFID). To study RFID performance, it is necessary to obtain RFID tags' coordinates. However, the positioning method of RFID technology has large errors, and is easily affected by the environment. Therefore, a new method using optical measurement is proposed to achieve RFID performance analysis. First, due to the possibility of blurring during image acquisition, the paper derives a new image prior to removing blurring. A nonlocal means-based method for image deconvolution is proposed. Experimental results show that the PSNR and SSIM indicators of our algorithm are better than those of a learning deep convolutional neural network and fast total variation. Second, an RFID dynamic testing system based on photoelectric sensing technology is designed. The reading distance of RFID and the three-dimensional coordinates of the tags are obtained. Finally, deep learning is used to model the RFID reading distance and tag distribution. The error is 3.02%, which is better than other algorithms such as a particle-swarm optimization back-propagation neural network, an extreme learning machine, and a deep neural network. The paper proposes the use of optical methods to measure and collect RFID data, and to analyze and predict RFID performance. This provides a new method for testing RFID performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.69-72
• /
• 2024

모델 역추론 공격은 공격 대상 네트워크를 훈련하기 위해 사용되는 훈련 데이터셋 중 개인 데이터셋을 공개 데이터셋을 사용하여 개인 훈련 데이터셋을 복원하는 것이다. 모델 역추론 방법 중 적대적 생성 신경망을 사용하여 모델 역추론 공격을 하는 과거의 논문들은 딥러닝 모델 전체의 역추론에만 초점을 맞추기 때문에, 이를 통해 얻은 원본 이미지의 개인 데이터 정보는 제한적이다. 따라서, 본 연구는 대상 모델의 중간 출력을 사용하여 개인 데이터에 대한 더 품질 높은 정보를 얻는데 초점을 맞춘다. 본 논문에서는 적대적 생성 신경망 모델이 원본 이미지를 생성하기 위해 사용되는 계층별 역추론 공격 방법을 소개한다. MNIST 데이터셋으로 훈련된 적대적 생성 신경망 모델을 사용하여, 원본 이미지가 대상 모델의 계층을 통과하면서 얻은 중간 계층의 출력 데이터를 기반으로 원본 이미지를 재구성하고자 한다. GMI 의 공격 방식을 참고하여 공격 모델의 손실 함수를 구성한다. 손실 함수는 사전 손실 및 정체성 손실항을 포함하며, 역전파를 통해서 원본 이미지와 가장 유사하게 복원할 수 있는 표현 벡터 Z 를 찾는다. 원본 이미지와 공격 이미지 사이의 유사성을 분류 라벨의 정확도, SSIM, PSNR 값이라는 세 가지 지표를 사용하여 평가한다. 공격이 이루어지는 계층에서 복원한 이미지와 원본 이미지를 세 가지 지표를 가지고 평가한다. 실험 결과, 공격 이미지가 원본 이미지의 대상 분류 라벨을 정확하게 가지며 원본 이미지의 필체를 유사하게 복원하였음을 보여준다. 평가 지표 또한 원본 이미지와 유사하다는 것을 나타낸다.

• Current Optics and Photonics
• /
• v.8 no.5
• /
• pp.463-471
• /
• 2024

Multimode fibers (MMFs) possess high information throughput and small core diameter, making them highly promising for applications such as endoscopy and communication. However, modal dispersion hinders the direct use of MMFs for image transmission. By training neural networks on time-series waveforms collected from MMFs it is possible to reconstruct images, transforming blurred speckle patterns into recognizable images. This paper proposes a fully convolutional neural-network model, MSMDFNet, for image restoration in MMFs. The network employs an encoder-decoder architecture, integrating multiscale convolutional modules in the decoding layers to enhance the receptive field for feature extraction. Additionally, attention mechanisms are incorporated from both spatial and channel dimensions, to improve the network's feature-perception capabilities. The algorithm demonstrates excellent performance on MNIST and Fashion-MNIST datasets collected through MMFs, showing significant improvements in various metrics such as SSIM.

• Nuclear Engineering and Technology
• /
• v.56 no.10
• /
• pp.4227-4236
• /
• 2024

Nuclear energy is used more and more widely as a clean energy source, but nuclear energy facilities are risky, and when a nuclear leak occurs, it is necessary to detect equipment in a nuclear radiation environment. In the nuclear radiation environment, due to the impact of high-energy particles on the camera sensor, the collected image contains a lot of radiation noise, which greatly reduces the visual perception of the image. Aiming at the problem that radiation noise reduces image quality, a radiation image compound filtering algorithm combining median filtering and multi-frame average filtering is proposed based on radiation noise characteristics. Compared with several common filtering algorithms, the radiation noise image is filtered under the same radiation dose and achieve the highest Peak Signal Noise Rate (PSNR) and Structural Similarity (SSIM), and compared with the multi-frame average filtering method, the number of image frames required by the algorithm in this paper is greatly reduced. Experimental results show that the algorithm can effectively eliminate radiation noise and is more suitable for image filtering in radiation environment.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.138-145
• /
• 2018

In this paper, we propose a new motion estimation algorithm for frame rate up-conversion. The proposed algorithm uses the variance of errors in addition to SAD in motion estimation to find more accurate motion vectors. Then, it decides which motion vectors are wrong using the variance of neighbor motion vectors and the variance between current motion vector and neighbor's average motion vector. Next, incorrect motion vectors are corrected by weighted sum of eight neighbor motion vectors. Additionally, we propose adaptive search range algorithm, so we can find more accurate motion vectors and reduce computational complexity at the same time. As a result, proposed algorithm improves the average peak signal-to-noise ratio and structural similarity up to 1.44 dB and 0.129, respectively, compared with previous algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1689-1703
• /
• 2020

When data is transmitted over an unreliable channel, the error of the data packet may result in serious degradation. The multiple description coding (MDC) can solve this problem and save transmission costs. In this paper, we propose a deep multiple description coding network (MDCN) to realize efficient image compression. Firstly, our network framework is based on convolutional auto-encoder (CAE), which include multiple description encoder network (MDEN) and multiple description decoder network (MDDN). Secondly, in order to obtain high-quality reconstructed images at low bit rates, the encoding network and decoding network are integrated into an end-to-end compression framework. Thirdly, the multiple description decoder network includes side decoder network and central decoder network. When the decoder receives only one of the two multiple description code streams, side decoder network is used to obtain side reconstructed image of acceptable quality. When two descriptions are received, the high quality reconstructed image is obtained. In addition, instead of quantization with additive uniform noise, and SSIM loss and distance loss combine to train multiple description encoder networks to ensure that they can share structural information. Experimental results show that the proposed framework performs better than traditional multiple description coding methods.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.6
• /
• pp.609-617
• /
• 2020

Non-destructive inspection using X-rays is used as a method to check the inside of products. In order to accurately inspect, a X-ray image requires a higher spatial resolution. However, the reduction in pixel size of the X-ray detector, which determines the spatial resolution, is time-consuming and expensive. In this regard, a DMM has been proposed to obtain an improved spatial resolution using the same X-ray detector. However, this has a limitation that the motion blur phenomenon, which is a decrease in spatial resolution. In this paper, motion blur was removed by applying Non-Blind Deconvolution to the DMM image, and the increase in spatial resolution was confirmed. DMM and Non-Blind Deconvolution were sequentially applied to X-ray images, confirming 62 % MTF value by an additional 29 % over 33 % of DMM only. In addition, SSIM and PSNR were compared to confirm the similarity to the 1/2 pixel detector image through 0.68 and 33.21 dB, respectively.