• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.29-39
• /
• 2022

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted high-resolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The Recall reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The IoU of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The IoU of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the IoU by 2.9%. In general, our method is of great significance for crack detection.

• Journal of Korean Neurosurgical Society
• /
• v.65 no.6
• /
• pp.868-874
• /
• 2022

Spontaneous intracranial hypotension (SIH) most commonly manifests as bilateral subdural hematoma (SH). SIH cases mostly resolve spontaneously but further treatment would be needed via blind epidural blood patch (EBP). Cerebrospinal fluid (CSF) leakage in EBP-refractory cases can be treated surgically only if the localization of CSF leakage is detectable but it cannot be possible in most of the cases. Also surgical evacuation of SH secondary to SIH (SH-SIH) is not favorable without blocking the CSF leakage. Thus the management of these patients is a challenge and alternative treatment options are needed. Although middle meningeal artery embolization (MMAE) is an effective treatment option in non-SIH SH, there is no report about its application in the treatment of SH-SIH. We present two cases of SH-SIH which their clinical and radiological findings were completely resolved by bilateral MMAE treatment.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.29-36
• /
• 2019

When dealing with outdoor images in a variety of computer vision applications, the presence of shadow degrades performance. In order to understand the information occluded by shadow, it is essential to remove the shadow. To solve this problem, in many studies, involves a two-step process of shadow detection and removal. However, the field of shadow detection based on CNN has greatly improved, but the field of shadow removal has been difficult because it needs to be restored after removing the shadow. In this paper, it is assumed that shadow is detected, and shadow-less image is generated by using original image and shadow mask. In previous methods, based on CGAN, the image created by the generator was learned from only the aspect of the image patch in the adversarial learning through the discriminator. In the contrast, we propose a novel method using a discriminator that judges both the whole image and the local patch at the same time. We not only use the residual generator to produce high quality images, but we also use joint loss, which combines reconstruction loss and GAN loss for training stability. To evaluate our approach, we used an ISTD datasets consisting of a single image. The images generated by our approach show sharp and restored detailed information compared to previous methods.

• 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.

• Journal of Advanced Navigation Technology
• /
• v.24 no.6
• /
• pp.601-606
• /
• 2020

In this paper, we designed a microstrip patch antenna that can be applied to the Wimax/LTE 5G system among wireless media usable in coastal ships. The substrate of the proposed antenna is FR-4 (er=4.3), the size is 22 mm × 30 mm, and it can be used in the 3.5 GHz and 5.8 GHz bands of Wimax/LTE 5G by constructing a simple structure using a microstrip patch antenna. CST Microwave Studio 2014 was used for simulation, and the gain of the simulation result is 2.41dB at 2.4 GHz and 3.96 dB at 3.5 GHz. S-Parameter also showed a result of less than -10 dB (VSWR 2:1) in the desired frequency band, and designed a small variable and a miniaturized antenna so that the antenna can be used in mobile phones or electronic devices.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.295-302
• /
• 2010

Example-based super resolution(EBSR) is a method to reconstruct high-resolution images by learning patch-wise correspondence between high-resolution and low-resolution images. It can reconstruct a high-resolution from just a single low-resolution image. However, when it is applied to a text image whose font type and size are different from those of training images, it often produces lots of noise. The primary reason is that, in the patch matching step of the reconstruction process, input patches can be inappropriately matched to the high-resolution patches in the patch dictionary. In this paper, we propose a new patch matching method to overcome this problem. Using an image observation model, it preserves the correlation between the input and the output images. Therefore, it effectively suppresses spurious noise caused by inappropriately matched patches. This does not only improve the quality of the output image but also allows the system to use a huge dictionary containing a variety of font types and sizes, which significantly improves the adaptability to variation in font type and size. In experiments, the proposed method outperformed conventional methods in reconstruction of multi-font and multi-size images. Moreover, it improved recognition performance from 88.58% to 93.54%, which confirms the practical effect of the proposed method on recognition performance.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.6
• /
• pp.635-642
• /
• 2019

Objective : The aim of this study was to investigate the biomechanical differences between human dura mater and dura mater substitutes to optimize biomimetic materials. Methods : Four groups were investigated. Group I used cranial dura mater (n=10), group II used $Gore-Tex^{(R)}$ Expanded Cardiovascular Patch (W.L. Gore & Associates Inc., Flagstaff, AZ, USA) (n=6), group III used $Durepair^{(R)}$ (Medtronic Inc., Goleta, CA, USA) (n=6), and group IV used $Tutopatch^{(R)}$ (Tutogen Medical GmbH, Neunkirchen am Brand, Germany) (n=6). We used an axial compression machine to measure maximum tensile strength. Results : The mean tensile strengths were $7.01{\pm}0.77MPa$ for group I, $22.03{\pm}0.60MPa$ for group II, $19.59{\pm}0.65MPa$ for group III, and $3.51{\pm}0.63MPa$ for group IV. The materials in groups II and III were stronger than those in group I. However, the materials in group IV were weaker than those in group I. Conclusion : An important dura mater graft property is biomechanical similarity to cranial human dura mater. This biomechanical study contributed to the future development of artificial dura mater substitutes with biomechanical properties similar to those of human dura mater.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.22 no.2
• /
• pp.83-100
• /
• 2004

In this paper, the quantity of dot gain in off-set printing is estimated by using the method of UCR(under color removal) and GCR(gray component replacement) and the degree of dot gain is researched through measurement of dot coverage of each color patch at the output film that is variously applied to discretionary quantity of dot gain each line in screen in the printing for the process of color separation and at the offset printing. Also, the best appropriate quantity of dot gain treatment is examined by printing each line in screen for reproduction of colors.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.217-220
• /
• 2018

본 논문에서는 딥러닝을 활용한 비디오 보간법(video interpolation)에 대한 최근 모델들을 HD 급 비디오로 학습시키는 방법과 평가 성능을 비교 분석하는 것을 목표로 한다. 기존의 딥러닝을 활용한 비디오 보간법에 대해 제안된 모델들은 낮은 해상도의 비디오로 실험을 진행하였다. 반면 본 연구에서는 한정된 메모리를 가지고도 높은 해상도의 비디오를 학습시키기 위해서 패치 단위 데이터 셋을 구성하여 학습을 진행하였다. 평가 성능을 보이기 위해서 학습 데이터와 마찬가지로 패치 단위 평가와 전체 프레임 단위 평가 성능의 결과를 비교한다.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1034-1042
• /
• 2016

Together with machine-learning frameworks, area-based imagery registration techniques can be easily applied to diverse types of image pairs without predefined features and feature descriptors. However, feature detectors are often used to quickly identify candidate image patch pairs, limiting the applicability of these registration techniques. In this paper, we propose a ConvNet (Convolutional Network) "Dart" that provides not only the matching metric between patches, but also information about their distance, which are helpful in reducing the search space of the corresponding patch pairs. In addition, we propose a ConvNet "Fad" to identify the patches that are difficult for Dart to improve the accuracy of registration. These two networks were successfully implemented using Deep Learning with the help of a number of training instances generated from a few registered image pairs, and were successfully applied to solve a simple image registration problem, suggesting that this line of research is promising.