• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.4
• /
• pp.351-359
• /
• 2009

We have developed a computer simulator fur cone-beam computed tomography (CBCT) based on the commercial Monte Carlo code, MCNP. All the functions to generate input files, run MCNP, convert output files to image data, reconstruct tomographs were realized in graphical user-interface form. The performance of the simulator was demonstrated by comparing with the experimental data. Although some discrepancies were observed due to the ignorance of the detailed physics in the simulation, such as scattered X-rays and noise in image sensors, the overall tendency was well agreed between the measured and simulated data. The developed simulator will be very useful for understanding the operation and the better design of CT systems.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.197-205
• /
• 2009

With the introduction of the computer, convenience at work may have increased but flexibility decreased along with a tendency for humans to become secondary to computers with regards to work schedules. As it exists, from entering the department of radiology to completion of imaging requires a great deal of time and difficulties in understanding the imaging process adds to patient dissatisfaction. Since clinics use RFID bars to track patient locations at comprehensive medical testing centers, departments of radiology may apply RFID and Worklist at the core of the OCS system in order to increase work efficiency and improve work flow. As a result of developing an RFID and Worklist centered OCS program, there was a vast improvement in patient satisfaction and work flow. Theses results are the basis of an RFID system that in the future may be connected to PACS and other systems with an intergrated Worklist. There is a need to realize a plan the can offer ubiquity to hospital work.

• Journal of the Korea Computer Graphics Society
• /
• v.7 no.2
• /
• pp.29-35
• /
• 2001

In general, image-based virtual environment is represented by panoramic images created by image mosaic algorithm. The cylindrical panoramic image supports the fixed-viewpoint navigation due to the constraints of construction. Shum proposed concentric mosaics to allow users to navigate freely within a circular area[10]. It is constructed by a sequence of images which is acquired from a regularly rotating camera. Concentric mosaics technique, proposed by Shum, is considered as 3D plenoptic function which is defined three parameters : distance, height and angle. In this paper, we suggest an effective method for creating concentric mosaics, in which we first align a set of strip images on the cylinder plane and stitch the aligned strips to build a panoramic image. The proposed method has no constraints such as regular panning motion of camera. Furthermore, our proposed method minimizes the use of interpolation image to create a novel view images from the concentric mosaics. It allows the result image on a novel view to have better quality with respect to the number of input images.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.127-135
• /
• 2020

In this paper, we propose an IoT-enabled solution for tour photography services with small-size investment and resources in the travel and tourism industries, being able to impact on economic, social, and cultural values. An IoT-enabled camera is developed based on an open hardware and software platform complying with oneM2M, which can make traditional embedded systems oneM2M-compliant devices due to a middleware solution called TAS (thing adaptation software). IoT cameras deployed around photo zones in a tour site could be remotely controlled via an IoT gateway with a Web-based application on a smartphone. Users would perform a pan and tilt camera control if they want and then take and download a perfect photo picture (even though they are away from the tour site). We expect that the proposed solution will promote the deployment IoT-enabled technologies in tour and travel industries which are important parts of the tertiary sector.

• The Journal of Korean Academy of Prosthodontics
• /
• v.57 no.4
• /
• pp.425-431
• /
• 2019

This clinical case report describes the digital workflow that combines a face scan, cone beam computed tomography and an intraoral scan to visualize the outcome of prosthodontic treatment in the anterior region. This approach improves communication between clinic, laboratory and patients. A patient with healthy general condition came for a restorative treatment to treat post-traumatic central incisors of maxilla. A virtual patient replica was made by incorporating a face scan, cone beam computed tomography and an intraoral scan. Design mockup of definitive restorations was shown to the patient and modified according to the patient's desire. This digital workflow facilitates the fabrication of optimal esthetic restorations, and enhances the predictability of outcome of restorations.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.19-28
• /
• 2021

Esophagogastroduodenoscopy is a method commonly used for early diagnosis of upper gastrointestinal lesions. However, 10-20 percent of the gastric lesions are reported to be missed, due to human error. And countries including the US, the UK, and Japan, the World Endoscopy Organization (WEO) suggested guidelines about essential gastrointestinal parts to take pictures of so that all gastric lesions are observed. In this paper, we propose deep learning techniques for classification of anatomical sites, aiming for the system that informs practitioners whether they successfully did the gastroscopy without blind spots. The proposed model uses pre-processing modules and data augmentation techniques suitable for gastroscopy images. Not only does the experiment result with a maximum F1 score of 99.6%, but it also shows a error rate of less than 4% based on the actual data. Given the performance results, we found the model to be explainable with the potential to be utilized in the clinical area.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.619-625
• /
• 2022

In the field of imaging medicine, computed tomography is one of the most common test methods and one of the most frequently used test methods in hospitals. However, it is accompanied by a very high radiation exposure compared to other test methods. In order to reduce exposure, CT scans should be performed only when absolutely necessary, and even if the tests are performed because they are absolutely necessary, a protocol that serves the purpose of the test and allows the test to be performed in a small dose should be used. In this study, we wanted to learn about the most up-to-date radiation dose usage information used by the region's leading general hospitals and develop a diagnostic reference level (DRL). In the experimental results, the Head CT and Abdomen CT tests showed that DLP was higher than the NRPB (U.K) and Korean DRL. The DLP values used by Chest CT were low for all 3 types of CT devices. The hospital found that efforts to reduce exposure should be made during CT examinations, and in particular, Head CT and Abdomen CT determined that efforts to reduce exposure were necessary.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.33-40
• /
• 2022

In this paper, we propose a system that analyzes drone photographic images of panel-type factory roofs and conducts abnormal detection of bolts. Currently, inspectors directly climb onto the roof to carry out the inspection. However, safety accidents caused by working conditions at high places are continuously occurring, and new alternatives are needed. In response, the results of drone photography, which has recently emerged as an alternative to the dangerous environment inspection plan, will be easily inspected by finding the location of abnormal bolts using deep learning. The system proposed in this study proceeds with scanning the captured drone image using a sample image for the situation where the bolt cap is released. Furthermore, the scanned position is discriminated by using AI, and the presence/absence of the bolt abnormality is accurately discriminated. The AI used in this study showed 99% accuracy in test results based on VGGNet.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.85-90
• /
• 2022

In this study, to reduce the time and cost disadvantages of the traditional motion graphic production method in order to realize the movement of a virtual camera identical to that of the real camera, motion graphics virtualization using AR Core-based mobile device real-time tracking data A method for creating a camera is proposed. The proposed method is a method that simplifies the tracking operation in the video file stored after shooting, and simultaneously proceeds with shooting on an AR Core-based mobile device to determine whether or not tracking is successful in the shooting stage. As a result of the experiment, there was no difference in the motion graphic result image compared to the conventional method, but the time of 6 minutes and 10 seconds was consumed based on the 300frame image, whereas the proposed method has very high time efficiency because this step can be omitted. At a time when interest in image production using virtual augmented reality and various studies are underway, this study will be utilized in virtual camera creation and match moving.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.153-161
• /
• 2015

In this paper, we propose a locomotor evaluation System for mouse based on continuous shooting images. In the field of veterinary medicine and animal studies are subjected to using the mouse for the quality of human life. In particular, during the experiments using the artificially created mice injury, through a variety of scoring and a lot of experiments to measure the extent of recovery from the injury. The traditional method of measuring the quantity of exercise while in this experiment was made of a method for directly observing person. The proposed system performs the continuous shooting per unit of time specified by the movement of the mouse is extracted from a continuous image shooting with the outline of a mouse point cloud. And using the extracted point cloud to extract again the inner contour of the body of the mouse. So using the new point cloud obtained its center, Then, using the center point calculated by accumulating the distance between two points on locomotor evaluation system design and implement to obtain the total distance the mouse moves over a unit of time.