• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.659-660
• /
• 2021

본 논문에서는 데카르트 좌표계 기반으로 노드를 압축함으로써 SR(Super-resolution) 기반 연기 합성을 효율적으로 처리할 수 있는 방법을 제안한다. 제안하는 방법은 다운 스케일링과 이진화를 통하여 연기 시뮬레이션의 계산 공간을 효율적으로 줄이고, 데카르트 좌표계 축을 기준으로 쿼드트리의 말단 노드를 압축함으로써 네트워크의 입력으로 전달하는 데이터 개수를 줄인다. 학습에 사용된 데이터는 COCO 2017 데이터셋이며, 인공신경망은 VGG19 기반 네트워크를 사용한다. 컨볼루션 계층을 거칠 때 데이터의 손실을 막기 위해 잔차(Residual)방식과 유사하게 이전 계층의 출력 값을 더해주며 학습한다. 결과적으로 제안하는 방법은 이전 결과에 비해 네트워크로 전달해야 하는 데이터가 압축되어 개수가 줄어드는 결과를 얻었으며, 그로 인해 네트워크 단계에서 필요한 I/O 과정을 효율적으로 처리할 수 있게 되었다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.62-69
• /
• 2019

Electrocardiogram (ECG) signals cannot be counterfeited and can easily acquire signals from both wrists. In this paper, we propose a method of generating a coupling image using direction information of ECG signals as well as its usage in a personal recognition method. The proposed coupling image is generated by using forward ECG signal and rotated inverse ECG signal based on R-peak, and the generated coupling image shows a unique pattern and brightness. In addition, R-peak data is increased through the ECG signal calculation of the same beat, and it is thus possible to improve the recognition performance of the individual. The generated coupling image extracts characteristics of pattern and brightness by using the proposed convolutional neural network and reduces data size by using multiple pooling layers to improve network speed. The experiment uses public ECG data of 47 people and conducts comparative experiments using five networks with top 5 performance data among the public and the proposed networks. Experimental results show that the recognition performance of the proposed network is the highest with 99.28%, confirming potential of the personal recognition.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.17-27
• /
• 2022

In this study, a deep learning-based network that can predict the aerodynamic characteristics of airfoils was designed, and the feasibility of the proposed network was confirmed by applying aerodynamic data generated by Xfoil. The prediction of aerodynamic characteristics according to the variation of airfoil thickness was performed. Considering the angle of attack, the coordinate data of an airfoil is converted into image data using signed distance function. Additionally, the distribution of the pressure coefficient on airfoil is expressed as reduced data via proper orthogonal decomposition, and it was used as the output of the proposed network. The test data were constructed to evaluate the interpolation and extrapolation performance of the proposed network. As a result, the coefficients of determination of the lift coefficient and moment coefficient were confirmed, and it was found that the proposed network shows benign performance for the interpolation test data, when compared to that of the extrapolation test data.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.4
• /
• pp.221-232
• /
• 2023

This paper presents a novel convolutional neural network (CNN)-based approach for predicting bolt clamping force in the early bolt loosening state of bolted structures. The approach entails tightening eight bolts with different clamping forces and generating frequency responses, which are then used to create a similarity map. This map quantifies the magnitude and shape similarity between the frequency responses and the initial model in a fully fastened state. Krylov subspace-based model order reduction is employed to efficiently handle the large amount of frequency response data. The CNN model incorporates a regression output layer to predict the clamping forces of the bolts. Its performance is evaluated by training the network by using various amounts of training data and convolutional layers. The input data for the model are derived from the magnitude and shape similarity map obtained from the frequency responses. The results demonstrate the diagnostic potential and effectiveness of the proposed approach in detecting early bolt loosening. Accurate bolt clamping force predictions in the early loosening state can thus be achieved by utilizing the frequency response data and CNN model. The findings afford valuable insights into the application of CNNs for assessing the integrity of bolted structures.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.106-109
• /
• 2021

본 논문에서는 입력에 따라 합성곱 레이어 간의 잔차 연결을 변화시키는 동적 잔차 연결을 활용해 고해상도 복원 (Super-resolution) 작업을 위한 경량 네트워크를 설계하는 방법을 제안한다. 먼저, 동적 잔차 연결을 입력에 따라 변화시킬 수 있도록 경량화된 (Lightweight) 모듈을 설계하는 방법을 제안한다. 또한 이렇게 설계한 모듈로부터 얻은 잔차 연결에 대한 정보를 토대로 네트워크를 설계하는 방법을 제시한다. 제안된 방법을 통해 설계된 고해상도 복원 작업을 위한 네트워크는 적은 파라미터로도 입력에 따라 적응적으로 네트워크의 구조를 변화시킬 수 있어 효울적으로 다양한 입력 영상을 처리할 수 있다.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.961-973
• /
• 2020

In this manuscript, a new pansharpening model based on Convolutional Neural Network (CNN) was developed. Dilated convolution, which is one of the representative convolution technologies in CNN, was applied to the model by making it deep and complex to improve the performance of the deep learning architecture. Based on the dilated convolution, the residual network is used to enhance the efficiency of training process. In addition, we consider the spatial correlation coefficient in the loss function with traditional L1 norm. We experimented with Dilated Residual Networks (DRNet), which is applied to the structure using only a panchromatic (PAN) image and using both a PAN and multispectral (MS) image. In the experiments using KOMPSAT-3A, DRNet using both a PAN and MS image tended to overfit the spectral characteristics, and DRNet using only a PAN image showed a spatial resolution improvement over existing CNN-based models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.355-363
• /
• 2020

In this paper, we propose a deep learning training method for accurately classifying Kuzushiji-MNIST and Kuzushiji-49 datasets for ancient and medieval Japanese characters. We analyze the latest convolutional neural network networks through experiments to select the most suitable network, and then use the networks to select the number of training to classify Kuzushiji-MNIST and Kuzushiji-49 datasets. In addition, the training is conducted with high accuracy by applying learning methods such as Mixup and Random Erase. As a result of the training, the accuracy of the proposed method can be shown to be high by 99.75% for MNIST, 99.07% for Kuzushiji-MNIST, and 97.56% for Kuzushiji-49. Through this deep learning-based technology, it is thought to provide a good research base for various researchers who study East Asian and Western history, literature, and culture.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.4-7
• /
• 2022

기존 합성곱 신경망 기반의 잡음 제거 네트워크들은 학습을 위한 noisy-clean 데이터 쌍을 필요로 한다. 하지만 실제 카메라 잡음의 경우, 잡음에 대한 깨끗한 원본 영상을 얻는 것은 불가능하거나 많은 비용이 소모된다. 따라서 이러한 방법을 해결하기 위하여 원본 영상 없이 잡음 영상만으로만 잡음 제거 네트워크를 학습하는 방법들이 제안되어왔다. 그 중 카메라 잡음 영상을 처리하기 위한 대표적인 방법으로 학습과 추론에서 비대칭적인 downsampling을 사용하는 AP-BSN이 제안되었다. 본 논문에서는 Functional neural network를 AP-BSN 알고리즘에 적용하여 다양한 downsampling ratio에 대응되는 하나의 네트워크를 학습하였다. 이를 통해 기존 hyperparameter로 사용되던 downsampling ratio에 대한 결과를 하나의 네트워크에서 분석 및 확인하였다. 또한 해당 파라미터를 조절함으로써 다양한 잡음 제거 후보들을 추출하고 사용자가 원하는 잡음 제거 정도를 조정할 수 있도록 하였다.