• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.177-185
• /
• 2022

A method of restoring the occluded area was proposed by referring to images taken with the same types of sensors on high-resolution optical satellite images through deep learning. For the natural continuity of the simulated image with the occlusion region and the surrounding image while maintaining the pixel distribution of the original image as much as possible in the patch segmentation image, CycleGAN (Cycle Generative Adversarial Network) method with ConvNeXt block applied was used to analyze three experimental regions. In addition, We compared the experimental results of a training patch size of 512*512 pixels and a 1024*1024 pixel size that was doubled. As a result of experimenting with three regions with different characteristics,the ConvNeXt CycleGAN methodology showed an improved R² value compared to the existing CycleGAN-applied image and histogram matching image. For the experiment by patch size used for training, an R² value of about 0.98 was generated for a patch of 1024*1024 pixels. Furthermore, As a result of comparing the pixel distribution for each image band, the simulation result trained with a large patch size showed a more similar histogram distribution to the original image. Therefore, by using ConvNeXt CycleGAN, which is more advanced than the image applied with the existing CycleGAN method and the histogram-matching image, it is possible to derive simulation results similar to the original image and perform a successful simulation.

• Structural Monitoring and Maintenance
• /
• v.6 no.4
• /
• pp.291-315
• /
• 2019

Fatigue cracks are inevitable in circumstances in which the cyclic loading exists. Therefore, many of mechanical components are in a risk of being in exposure to fatigue cracks. On the other hand, renewing the facilities or infrastructures is not always possible. Therefore, retrofitting the structures by means of the available methods, such as crack arrest methods is logical and in some cases inevitable. In this regard, this paper considers three popular crack arrest methods (e.g., drilling stop-hole, steel welded patch, and carbon fiber reinforced (CFRP) patch), which have been compared by using extended finite element method (XFEM). In addition, effects in terms of the width and thickness of patches and the configuration of drilling stop holes have been evaluated. Test results indicated that among the considered methods, CFRP patches were the most effective means for arresting cracks. Besides, in the case of arresting by means of drilling stop holes, drilling two holes next to the crack-tip was more effective than blunting the crack-tip by drilling one hole. In other words, the results indicated that the use of symmetric welded metal patches could lead to a 21% increase in fatigue life, as compared to symmetric stop holes. Symmetric CFRP patches enhanced the fatigue life of cracked specimen up to 77%, as compared to drilling symmetric stop holes. In addition, in all cases, symmetric configurations were far better than asymmetric ones.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.75-81
• /
• 2010

The segmentation of cartilage is crucial for the diagnose and treatment of osteoarthritis (OA), and has mostly been done manually by an expert, requiring a considerable amount of time and effort due to the thin shape and vague boundaries of the cartilage in MR (magnetic resonance) images. In this paper, we propose a fully automatic method to segment cartilage in a knee joint on MR images. The proposed method is based on a small number of manually segmented images as the training set and comprised of an initial per patch segmentation process and a global refinement process on the cumulative per patch results. Each patch for per patch segmentation is positioned by classifying the bone-cartilage interface on the pre-segmented bone surface. Next, the shape and intensity priors are constructed for each patch based on information extracted from reference patches in the training set. The ratio of influence between the shape and intensity priors is adaptively determined per patch. Each patch is segmented by graph cuts, where energy is defined based on constructed priors. Finally, global refinement is conducted on the global cartilage using the results of per patch segmentation as the shape prior. Experimental evaluation shows that the proposed framework provide accurate and clinically useful segmentation results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.471-472
• /
• 2012

The active shape model(ASM) is one of the most popular methods among the shape prior based segmentation methods based on its strong shape constraints using the statistic of shape information which is acquired from the training set. ASM has a few drawbacks, such as, the lack of shape variability, and the sensitivity for false locally searched points. In this paper, we suggest the patch-wise robust ASM to overcome the limitations of the ASM. In addition to the SSM, we introduce the patch-wise SSM, to reduce the shape inflexibility and to search reliable points with the point reliance measurement. The quantitative and qualitative results show the robustmness and the accuracy of the proposed method.

• Journal of Chest Surgery
• /
• v.46 no.2
• /
• pp.135-137
• /
• 2013

An atrial septal defect is the most common type of congenital heart disease among adults. Surgical repair or percutaneous closure of the defect is the treatment options. Even though percutaneous closure seems to be less risky than surgical repair, it may result in fatal complications like device embolism, cardiac perforation and tamponade. Herein we report a case of the embolism of a device into the pulmonary artery after one hour of percutaneous closure in which the embolized device was surgically removed and the defect was closed with a pericardial patch.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• Journal of KIISE:Software and Applications
• /
• v.37 no.5
• /
• pp.386-393
• /
• 2010

A defect in an image is a set of pixels forming an irregular shape. Since a defect, in most cases, is not easy to be modeled mathematically, the defect detection problem still resides in a research area. If a given image, however, composed by certain patterns, a defect can be detected by the fact that a non-defect area should be explained by another patch in terms of a rotation, translation, and noise. In this paper, therefore, the defect detection method for a repeated multi-patterned image is proposed. The proposed defect detection method is composed of three steps. First step is the interest point detection step, second step is the selection step of a appropriate patch size, and the last step is the decision step. The proposed method is illustrated using SEM images of semiconductor wafer samples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3962-3980
• /
• 2019

To deal with single sample face recognition, this paper presents a patch based semi-supervised linear regression (PSLR) algorithm, which draws facial variation information from unlabeled samples. Each facial image is divided into overlapped patches, and a regression model with mapping matrix will be constructed on each patch. Then, we adjust these matrices by mapping unlabeled patches to $[1,1,{\cdots},1]^T$. The solutions of all the mapping matrices are integrated into an overall objective function, which uses ${\ell}_{2,1}$-norm minimization constraints to improve discrimination ability of mapping matrices and reduce the impact of noise. After mapping matrices are computed, we adopt majority-voting strategy to classify the probe samples. To further learn the discrimination information between probe samples and obtain more robust mapping matrices, we also propose a multistage PSLR (MPSLR) algorithm, which iteratively updates the training dataset by adding those reliably labeled probe samples into it. The effectiveness of our approaches is evaluated using three public facial databases. Experimental results prove that our approaches are robust to illumination, expression and occlusion.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.