• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.70-77
• /
• 2008

This paper proposes a new text candidate region detection method that uses genetic algorithm based on information of the segmented regions. In image segmentation, a classification of the pixels at each color channel and a reclassification of the region-unit for reducing inhomogeneous clusters are performed. EWFCM(Entropy-based Weighted C-Means) algorithm to classify the pixels at each color channel is an improved FCM algorithm added with spatial information, and therefore it removes the meaningless regions like noise. A region-based reclassification based on a similarity between each segmented region of the most inhomogeneous cluster and the other clusters reduces the inhomogeneous clusters more efficiently than pixel- and cluster-based reclassifications. And detecting text candidate regions is performed by genetic algorithm based on energy and variance of the directional edge components, the number, and a size of the segmented regions. The region information-based detection method can singles out semantic text candidate regions more accurately than pixel-based detection method and the detection results will be more useful in recognizing the text regions hereafter. Experiments showed the results of the segmentation and the detection. And it confirmed that the proposed method was superior to the existing methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.319-326
• /
• 2014

The accurate geo-referencing processes that apply ground control points is prerequisite for effective end use of HRSI (High-resolution satellite imagery). Since the conventional control point acquisition by human operator takes long time, demands for the automated matching to existing reference data has been increasing its popularity. Among many options of reference data, the airborne LiDAR (Light Detection And Ranging) data shows high potential due to its high spatial resolution and vertical accuracy. Additionally, it is in the form of 3-dimensional point cloud free from the relief displacement. Recently, a new matching method between LiDAR data and HRSI was proposed that is based on the image projection of whole LiDAR data into HRSI domain, however, importing and processing the large amount of LiDAR data considered as time-consuming. Therefore, we wmotivated to ere propose a local LiDAR chip generation for the HRSI geo-referencing. In the procedure, a LiDAR point cloud was rasterized into an ortho image with the digital elevation model. After then, we selected local areas, which of containing meaningful amount of edge information to create LiDAR chips of small data size. We tested the LiDAR chips for fully-automated geo-referencing with Kompsat-2 and Kompsat-3 data. Finally, the experimental results showed one-pixel level of mean accuracy.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.251-257
• /
• 2021

With the development of new media, great changes are taking place in the way people get information. The change is the use of video content that can deliver content in a more three-dimensional way than words or photos. After 2016, the number of live video streaming content providers and users has increased. In this paper the write takes the 1 personal live video streaming content as the research object. And the write takes live video streaming content on YouTube live or Douyu TV as a research example. In this paper, the writer analyzes the digital information content in the live video streaming case. And the writer expounds the necessity of these visual information and the characteristics of real-time live video streaming content. Especially since 2020, because of the influence of the COVID-19, the live video streaming industry has begun to combine with the traditional industry. It is expected that the integration of digital cutting-edge technology and live video streaming will not only provide diversity in the content, but also create more social value for the video content consumption culture. Therefore, The writer thinks it is necessary to conduct in-depth research on the social responsibility of real-time live content in the future.

• Geophysics and Geophysical Exploration
• /
• v.24 no.3
• /
• pp.113-130
• /
• 2021

Recently, ground-penetrating radar (GPR) surveys have been actively employed to obtain a large amount of data on occurrences such as ground subsidence and road safety. However, considering the cost and time efficiency, more intuitive and accurate interpretation methods are required, as interpreting a whole survey data set is a cost-intensive process. For this purpose, GPR data can be subjected to attribute analysis, which allows quantitative interpretation. Among the seismic attributes that have been widely used in the field of exploration, complex trace analysis and similarity are the most suitable methods for analyzing GPR data. Further, recently proposed attributes such as edge detecting and texture attributes are also effective for GPR data analysis because of the advances in image processing. In this paper, as a reference for research on the attribute analysis of GPR data, we introduce the useful attributes for GPR data and describe their concepts. Further, we present an analysis of the interpretation methods based on the attribute analysis and past cases.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.187-193
• /
• 2022

In the Yeongdong region of Gangwon-do, coastal areas are important resources in terms of cultural, social and economic aspects. However, the coast of Gangwon-do is experiencing severe erosion, and it is concerned that its adverse effects will gradually increase. In this study, coastline changes of Yangyang and Gangneung in Gangwon-do were tracked and analyzed over a long period of time. In order to build time series image data, aerial photos from the 1940s to the present were mainly used, and data from CORONA satellite, which operated from the 1960s to the early 1970s, were collected and used together. Using 51cm resolution ortho image and 2m resolution Digital Elevation Model(DEM) as reference, ground control points were selected to perform geometric correction on the aerial photos and CORONA images. Subsequently, Canny edge detector applied to these images to extract the coastlines. As a result of analyzing the extracted and vectorized coastlines by overlaying them in chronological order, erosion and deposition occurring around the artificial structures and on the nearby beaches were observed. In this study, the effect of seasonal variation, tide, and various coastal management including the beach filling were not considered. Because coastal erosion is greatly affected by geographic factors, each local government must find its own solution. Continuous research and local data accumulation are required.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.671-677
• /
• 2023

When a scintillator block is constructed using fine scintillator pixels, the scintillator block located at the edge of the scintillator block results in overlapping images. To solve this problem, a light guide was inserted between the scintillator block and the photosensor, and images of all scintillation pixels were separated and acquired. However, loss of light may occur through the light guide, which eventually affects the quality of the image due to a decrease in energy resolution. Therefore, in this study, a detector was designed that can separate scintilltion pixels better by using a reflector on the side of the light guide and can secre excellent energy resolution by minimizing light loss. For comparative evaluation with previous studies, flood images were obtained through DETECT2000 capable of light simulation, and the degree of separation and light collection rate were evaluated. When a reflector was used on the side of the light guide, all materials showed excellent separation regardless of the material of the light guide, which showed better separation results than previous studies. In addition, the light collection rate was more that five times better when the reflector was applied than when it wa not. If this detector is applied to a small animal positron emission tomography, it will be possilbe to secre excellent image quality through excellent spatial resolution and energy resolution.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.536-542
• /
• 2023

Satellites represent cutting-edge technology, of ering significant advantages in spatial and temporal observations. National agencies worldwide harness satellite data to respond to marine accidents and analyze ocean fluctuations effectively. However, challenges arise with high-resolution satellite-based sea surface temperature data (Operational Sea Surface Temperature and Sea Ice Analysis, OSTIA), where gaps or empty areas may occur due to satellite instrumentation, geographical errors, and cloud cover. These issues can take several hours to rectify. This study addressed the issue of missing OSTIA data by employing LaMa, the latest deep learning-based algorithm. We evaluated its performance by comparing it to three existing image processing techniques. The results of this evaluation, using the coefficient of determination (R²) and mean absolute error (MAE) values, demonstrated the superior performance of the LaMa algorithm. It consistently achieved R² values of 0.9 or higher and kept MAE values under 0.5 ℃ or less. This outperformed the traditional methods, including bilinear interpolation, bicubic interpolation, and DeepFill v1 techniques. We plan to evaluate the feasibility of integrating the LaMa technique into an operational satellite data provision system.

• Progress in Medical Physics
• /
• v.26 no.1
• /
• pp.6-11
• /
• 2015

The purpose of this study was to analyze the rotational errors of roll, pitch, and yaw in the whole breast cancer treated by the three-dimensional radiation therapy (3D-CRT) using TomoDirect (TD). Twenty-patient previously treated with TD 3D-CRT was selected. We performed a retrospective clinical analysis based on 80 images of megavoltage computed tomography (MVCT) including the systematic and random variation with patient setup errors and treatment setup margin (mm). In addition, a rotational error (degree) for each patient was analyzed using the automatic image registration. The treatment margin of X, Y, and Z directions were 4.2 mm, 6.2 mm, and 6.4 mm, respectively. The mean value of the rotational error for roll, pitch, and yaw were $0.3^{\circ}$, $0.5^{\circ}$, $0.1^{\circ}$, and all of systematic and random error was within $1.0^{\circ}$. The errors of patient positioning with the Y and Z directions have generally been mainly higher than the X direction. The percentage in treatment fractions in less than $2^{\circ}$ at roll, pitch, and yaw are 95.1%, 98.8%, and 97.5%, respectively. However, the edge of upper and lower (i.e., bottom) based on the center of therapy region (point) will quite a possibility that it is expected to twist even longer as the length of treatment region. The patient-specific characters should be considered for the accuracy and reproducibility of treatment and it is necessary to confirm periodically the rotational errors, including patient repositioning and repeating MVCT scan.