• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.99-112
• /
• 2019

Cracks on pavement surfaces are critical signs and symptoms of the degradation of pavement structures. Image-based pavement crack detection is a challenging problem due to the intensity inhomogeneity, topology complexity, low contrast, and noisy texture background. In this paper, we address the problem of pavement crack detection and segmentation at pixel-level based on a Deep Neural Network (DNN) using gray-scale images. We propose a novel DNN architecture which contains a modified U-net network and a high-level features network. An important contribution of this work is the combination of these networks afforded through the fusion layer. To the best of our knowledge, this is the first paper introducing this combination for pavement crack segmentation and detection problem. The system performance of crack detection and segmentation is enhanced dramatically by using our novel architecture. We thoroughly implement and evaluate our proposed system on two open data sets: the Crack Forest Dataset (CFD) and the AigleRN dataset. Experimental results demonstrate that our system outperforms eight state-of-the-art methods on the same data sets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.126-139
• /
• 2023

At present, naked-eye 3D appears more and more commonly on the facades of urban buildings. It brings an incredible visual experience to the audience by simulating the natural 3D 3D space effect. At the same time, it also creates enormous commercial value for city publicity and commercial advertisements. There is much research on naked-eye 3D visual effects, but for right-angle LED screens. Right-angle LED screen's brand-new expression method that has only become popular in recent years, how to convey a realistic naked-eye 3D effect through two LED screens combined at right angles has become a problem worth exploring. To explore the whole design ideas and production process of the naked-eye 3D impact of the right-angle LED screen, this paper is a preliminary study aimed at understanding the performance principle and expression features. Before the case analysis, first, understand the standard virtual 3D space construction techniques. Combining it with the optical illusion phenomenon, according to the expression principle of the naked-eye 3D effect of the right-angle LED screen, it can be summarized into seven expressions: Shadow, Color contrast, Background structure line, Magnify object, Object out of bounds, Object floating, Fusion of picture and background. By analyzing the optical illusion phenomenon used in the case, we summarized the main performance characteristics of the naked eye 3D effect. The emergence of right-angle LED screens breaks the limitation of a single plane of optical illusion art, perfectly combines building facades with naked-eye 3D visual effects, and provides designers with a brand-new creative platform. Understanding its production principles and main expressive features can help designers enter this innovative platform better.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• The korean journal of orthodontics
• /
• v.31 no.1 s.84
• /
• pp.71-83
• /
• 2001

The purpose of this study was to Prove that the medial edge epithelial cells covering the secondary palatal shelves were removed by apoptosis during palatal fusion. 12 mature female rats (Suprague-Dawley) were mated overnight with male rats and sacrificed on days 15.0, 16.5, 16.75, 17.0 of pregnancy. The embryos were removed from the uterus and the heads were embedded in paraffin. The paraffin blocks were sectioned and the sections were undergone H-E staining for general histologic feature and TdT staining for detection of apoptotic cells. The obtained results were as follows. k. In the section of 16.0 and 16.5 day embryos, the palatal shelves were prior to contact and no apoptotic cells wereobserved in the medial edge epithelium. At the initial contact of Palatal shelves, there was a few apoptotic cells in the fusing epithelium. 2. In the 16.75 day embryos, the samples that epithelial seams did not lost there continuity, apoptotic cells were rarely seen at the midline epithelial seam. In contrast, a lot of apoptotic cells were observed at epithelial triangles and the junction between palatal shelves and nasal septum. 3. In the 16,75 day embryos, the samples that epithelial seams lost their continuity and disrupted to epithelial islands, large number, of apoptotic cells were observed at epithelial islands and epithelial triangles. Some apoptotic cells were also observed at the oral, nasal epithelium near the midline. 4. In the 17.0 day embryos, most of epithelial islands were disappeared and mesenchymal confluence was achieved. Apoptotic cells were rarely observed in the mesenchymal tissue which replaced epithelial islands, but there were some apoptotic cells at the epithelial triangles, oral and nasal epithelium. From the results of the study, it was revealed that medial edge epithelial cells of fusing palate were removed by apoptosis. Apoptotic cells were found mainly in the disappearing midline epithelial seam and the oral and nasal epithelial triangles at some late stages of palatal fusion.

• The Journal of Engineering Geology
• /
• v.23 no.1
• /
• pp.29-36
• /
• 2013

The application of appropriate rehabilitation methods can improve the efficiency of clogged wells and extend their life. In this paper, we study the feasibility of well cleaning using high-voltage pulsed discharge, in which electrical energy is used to produce impulsive pressure in water, in contrast to conventional methods that employ chemical or pneumatic energy sources. This technique utilizes the compressive shock wave generated by the expansive force of hot, dense plasma that is produced during a pulsed discharge in the gap between electrodes immersed in water. Compared with conventional techniques, this method is simple, and easy to handle and control. Using a capacitive pulsed power system with an electrical energy of 200 J, an impulsive pressure of 10.7 MPa is achieved at the position 6 cm away from the discharge gap. The amplitude of the impulsive pressure was easily controlled by adjusting the charging voltage of the capacitor and was almost linearly proportional to peak discharge current. The technique achieved good results in cleaning feasibility tests with mock-up specimens similar to clogged well screens.

• Clinical and Experimental Pediatrics
• /
• v.54 no.9
• /
• pp.373-379
• /
• 2011

Purpose: 4-1BB (CD 137) is a costimulatory molecule expressed on activated T-cells. Repression by 4-1BB is thought to attenuate Th2-mediated allergic reactions. The aim of this study was to investigate the effect of 4-1BB on allergic airway inflammation in a murine asthma model. Methods: BALB/c mice were sensitized to and challenged with ovalbumin (OVA). Hu.4-1BB-Fc was administered 1 day before the first OVA sensitization or 1 day after the second OVA sensitization. Following antigen challenge, airway responsiveness to methacholine was assessed and bronchoalveolar lavage (BAL) fluid was analyzed. Total immunoglobulin (Ig) E, OVA-specific IgE, $IgG_1$, and $IgG_{2a}$ levels in sera were measured by enzyme-linked immunosorbent assay. Lung pathology was also evaluated. Results: In mice treated with Hu.4-1BB-Fc before the first OVA sensitization, there was a marked decrease in airway hyperresponsiveness, total cell count, and eosinophil count in the BAL fluid. In addition, Hu.4-1BB-Fc treatment decreased serum OVA-specific $IgG_1$ levels and increased serum $IgG_{2a}$ level significantly compared with the corresponding levels in mice sensitized to and challenged with OVA. Hu.4-1BB-Fc-treated mice also showed suppressed peribronchial and perivascular inflammatory cell infiltration. In contrast, treatment with Hu.4-1BB-Fc 1 day after sensitization had no effect on airway hyperresponsiveness and showed less suppression of inflammation in lung tissue. Conclusion: Administration of Hu.4-1BB-Fc can attenuate airway inflammation and hyperreactivity in a mouse model of allergic airway inflammation. In addition, administration before sensitization may be more effective. These findings suggest that 4-1BB may be a useful therapeutic molecule against asthma.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.1
• /
• pp.63-66
• /
• 2009

Purpose: ACR (American College of Radiology) offers variable parameters to PET/CT quality control by using ACR Phantom. ACR Phantom was made to evaluate parameters which are uniformity, attenuation, scatter, contrast and resolution. Manual analysis method wasn't good for the use of QC because values of parameter were changed as it may user and it takes long time to analysis. Ki-Chun Lim, a nuclear scientist in AMC, developed program that automatically analysis values of parameter by using ACR Phantom to overcome above problems. In this study, we evaluated automatic analysis program's usability, through the comparing SUV of each method, reproducibility of SUV when repeated analysis and the time required. Materials and Methods: Using Flangeless Esser PET Phantom, the ideal ratio of 4 : 1 hot cylinder and BKG but it actually showed a ratio of 3.89 to 1 hot cylinder and BKG. SIEMENS Biograph True Point 40 was used in this study. We obtained images using ACR phantom at Fusion WB PET Scan condition (2 min/bed) and 120 kV, 100 mAs CT condition. Using True X method, 3 iterations, 14 subsets, Gaussian filter, FWHM 4 mm and Zoom Factor 1.0, $168{\times}168$ image size. We obtained Max. & Min. SUV and SUV Mean values at Cylinder (8, 12, 16, 25 mm, Air, Bone, Water, BKG) by automatic program and obtained SUV by manual method. After that, we compared manual and automatic method. we estimate the time required from opened the image data to final work sheet was completed. Results: Automatic program always showed same result and same the time required. At 8, 12, 16 and 25 m cylinder, manual method showed 6.69, 3.46, 2.59, 1.24 CV values. The larger cylinder size became, the smaller CV became. In manual method, bone, air, water's CV were over 9.9 except BKG (2.32). Obtained CV of Mean SUV showed BKG was low (0.85) and bone was high (7.52). The time required was 45 second, 882 second respectably. Conclusions: As a result of difference automatic method and manual method, automatic method showed always same result, manual method showed that the smaller hot cylinders became, the lager CV became. Hot cylinders mean region size, the smaller hot cylinder size becomes we had some trouble in doing ROI poison setting. And it means increase in variation of SUV. The Study showed the time required of automatic method was shorten then manual method.

• Parasites, Hosts and Diseases
• /
• v.26 no.4
• /
• pp.229-238
• /
• 1988

In vitro culture of Toxoplasma gondii in HL-60 cells and cell-mediates immunity against Toxoplasma in dimethylsulfoxide(DMSO) -induced HL-60 cells, i.e., differentiation into granulocytes, were pursued. HL-60 calls were treated with various concentrations of DMSO, and 1.3%(v/v) for 3 day incubation was chosen as the optimal condition icy differentiation into granulocytes. The degree of differentiation was assayed in physiological and functional aspects in addition to morphological point. When treated with 1.3% DMSO for 3 days, HL-60 cells did not synthesiar DNA materials beyond background level, and showed active chemotactic response to chemotactic peptide, formal-methionyl-leucyl-phenylalanine(FMLP). Morphologically promyelocytes of high nuclearlcytoplasmic(NIC) ratio changed to granulocytes of relatively low WJC ratio. The relationships between HL-60 cells or DMSO-induced HL-60 cells and Toxoplasma were examined after stain with Giemsa and Buorescent dye (acridine orange). HL-60 cells did not show any sign of torso- plasmacidal activity but showed intracellular proliferation of Texoplasma to form rosette for 72 hr co-culture. In contrast, OMSO-induced HL-60 cells phagocytosed Toxoplasma within 1 hr, and performed a process of intracellular digestion of Toxoplasma thereafter. With the above results, it is suggested that phagosome-Iysosome fusion is one of the critical events for the parasitism by Toxoplasma or for susceptibility of host cells. The in vitro culture system of this study has offered a defined condition to study the protozoan parasite-host cell interactions.

• Journal of Life Science
• /
• v.30 no.11
• /
• pp.1012-1020
• /
• 2020

Remicade is a therapeutic biosimilar natural antibody in which the mouse variable domain has been linked to the human constant domain. It is a chimeric monoclonal antibody specific to tumor necrosis factor-alpha (TNF-α) and has been developed for the treatment of rheumatoid arthritis. To investigate the biological activity of the Remicade antibody, we carried out a bioinformatics study using a protein data bank to characterize the TNF-α antigen binding mechanism of the Remicade natural antibody. Because the production of the Remicade antibody is often limited by genetic instability of the natural antibody-producing cell, we generated a Remicade single-chain variable domain fragment antibody (Remicade) in which a heavy chain variable domain (VH) is joined with a light chain variable domain (VL) by a polypeptide linker. Furthermore, Remicade was fused to a leucine zipper (RemicadeScZip) for higher production and higher antigen-binding activity than Remicade. The Remicade and Remicade ScZip were expressed in Escherichia coli and purified by a Ni⁺-NTA-agarose column. As expected, the purified proteins had migrated as 28.80 kDa and 33.96 kDa in sodium dodecyl sulfate-polyacrylamide electrophoresis. The TNF-α antigen binding activity of Remicade was not observed by ELISA and western blot. In contrast, RemicadeScZip showed antigen-binding activity. Additional bio-layer interferometry analysis confirmed the antigen-binding activity of RemicadeScZip, suggesting that the leucine zipper stabilized the folding of RemicadeScZip in a denatured condition and improved the TNF-α antigenbinding activity.