• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.165-193
• /
• 2022

It can be said that digital technology is at the center of the change in the modern work environment. In particular, in general public institutions that prove their work with records produced by business management systems and document production systems, the record management system is also the work environment itself. Gimpo City applied for the 2021 public cloud leading project of the National Information Society Agency (NIA) to proactively respond to the 4th industrial revolution technology era and implemented a public cloud-based AI-OCR technology enhancement project with 330 million won in support of 330 million won. Through this, it was converted into data beyond the limitations of non-electronic records limited to search and image viewing that depend on standardized index values. In addition, a 98% recognition rate was realized by applying a new technology called AI-OCR. Since digital technology has been used to improve work efficiency, productivity, development cost, and record management service levels of internal and external users, we would like to share the direction of enhancing expertise in the record management and implementation of work environment innovation.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.140-161
• /
• 2022

Seismic data with missing traces are often obtained regularly or irregularly due to environmental and economic constraints in their acquisition. Accordingly, seismic data interpolation is an essential step in seismic data processing. Recently, research activity on machine learning-based seismic data interpolation has been flourishing. In particular, convolutional neural network (CNN) and generative adversarial network (GAN), which are widely used algorithms for super-resolution problem solving in the image processing field, are also used for seismic data interpolation. In this study, CNN-based algorithm, U-Net and GAN-based algorithm, and conditional Wasserstein GAN (cWGAN) were used as seismic data interpolation methods. The results and performances of the methods were evaluated thoroughly to find an optimal interpolation method, which reconstructs with high accuracy missing seismic data. The work process for model training and performance evaluation was divided into two cases (i.e., Cases I and II). In Case I, we trained the model using only the regularly sampled data with 50% missing traces. We evaluated the model performance by applying the trained model to a total of six different test datasets, which consisted of a combination of regular, irregular, and sampling ratios. In Case II, six different models were generated using the training datasets sampled in the same way as the six test datasets. The models were applied to the same test datasets used in Case I to compare the results. We found that cWGAN showed better prediction performance than U-Net with higher PSNR and SSIM. However, cWGAN generated additional noise to the prediction results; thus, an ensemble technique was performed to remove the noise and improve the accuracy. The cWGAN ensemble model removed successfully the noise and showed improved PSNR and SSIM compared with existing individual models.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.97-107
• /
• 2009

Television News has significant impact on the information analysis of viewers by delivering world news to anonymous individuals everyday. We need to pay more attention to resolution considering the fact that even slight facial expression and the dress of TV anchor can be noticed by viewers in the high definition age, called HD TV, by radical changes in broadcasting situation. As a result, the beauty of expression that lighting technology has is extremely important in the high definition age. In news broadcast, as a phenomenon according to this change in trend, people have been looking for change in order to break with traditional TV news production by adopting DLP(Digital Lighting Processing) or LED(Light Emitting Diode). This effort has contributed to creating proper picture quality appropriate for HD TV. Nowadays Digital imaging is creating new trend in TV news production method from traditional analog-based lighting environment thanks to the development of IT(Information Technology) and digitalized lighting equipment. This change has led to building of HD studio and appropriate sets and lighting system. There are film set and projector which projects image on the screen and PDP, LCD, and DLP which has been used widely in recent years and LED which is often used as background in news program as examples, which has appeared since 1990s with HD TV. In this article, I analyzed the KBS News 9 lnce 1990s with in order to research the influence of television image component on the alyzed the KBS of TV article, I. I wille uggest the category of TV anchor image formulation in delivering information by means of lnce 1990s with based on the analysis result.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.9
• /
• pp.509-518
• /
• 2017

The purpose of this study is to investigate the experience of recognition struggle, which is a positive interaction with Korean society, through the life history research of the researcher ' The study was conducted as a narrative - life history analysis method. Life history data were collected through in-depth interviews. As a result of the study, the lifetime of the life history research subject, as a result of the constant challenge, considered Korea as the opportunity land and voluntarily migrated to Korea. He can analyze Korea as a fierce life to gain recognition by utilizing positive adaptation strategies. In other words, through the positive interaction of recognition struggle, he negotiated with the mainstream society and established his identity through positive experiences. In addition, through group activities, we have endeavored to protect the rights of the individual as well as the whole society and to improve the image and to integrate with the mainstream society. Through this reconstruction of life history, we can understand the life situation of Chinese leaders and know about the qualities they want to receive in Korean society. Therefore, it is suggested that this reconstruction of life history implies social welfare practice.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.4
• /
• pp.403-413
• /
• 2017

The study was conducted to understand the meaning of the voluntary service experience of Korean-Chinese who living in South Korea and examine the reason of participating in voluntary activities. 8 people participated in the study, who come from volunteering groups in a Korean-Chinese compact community. Data were collected through in - depth interviews and participation observation. The collected data were categorized and analyzed according to Giorgi's hermeneutic phenomenological research method. As a result of the analysis, three sets of themes were drawn on the nature of their volunteering experience. Through their volunteer activities, they have been improving their images that have been damaged and stigmatized by the mainstream society. Through their volunteer activities, they have improved their self-esteem, got more information about the society and better adapted to Korean society. Moreover, through their volunteer activities, they have increased their sense of responsibility for Korean society and redefined their position in Korea. Given this, they expect the possibility of becoming a global citizen for the future. The meanings of volunteer experience of Chinese Koreans have been examined and discussed in this study, which indicated that the activation of the volunteer activities of migrants contributes positively to the integration of multicultural society.