• Journal of the Korean Graphic Arts Communication Society
• /
• v.25 no.2
• /
• pp.15-28
• /
• 2007

For the color offset printing, it starts with input of data. The past days, drum scanner or flat scanner used to input of data, but now it changes gradually into using of digital camera because digital camera become popular. The high quality digital camera saves as a data(RAW format), sRGB which have built in digital camera, or Adobe RGB format. sRGB of ICC(International Color Consortium) profile is a standard color gamut of digital camera. Distribution of color gamut in sRGB is less than Adobe RGB have a distribution in ICC profile. sRGB also can not be expressed in some specific part, because distribution of color gamut in sRGB is not able to cover all parts in ICC Profile of international standards CMYK. It is more popular to use Adobe RGB than sRGB to do high quality offset printing and software basis color setting in Europe and Japan. In spite of this data basis, there is a difficulty of doing color correction between the color proofing prints and the final prints. To see how the software color setting effects to RGB data, this thesis will use Gretag Macbeth ColorChecker 24 patch which has the most general natural color chart to compare sRGB and Adobe RGB to check the differences of color changes. It will use the several factors that came out from the process of making ICC Profile to figure out the optimum In-house profile. It also compares the differences of using matt paper and glossy paper to do best quality color proof offset printing, and how the Rendering Intent effects the proof print.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.

• Journal of the Korean Institute of Gas
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2019

Most oil refineries and chemical plants have flare systems designed to mitigate pressure rises in process facilities in case of emergencies that require the release of large amounts of gas due to sudden process shutdowns such as power outages. However, the rise of the flame of the flare system causes civil complaints from residents around the factory due to visible pollution, and economic loss occurs in the company, which requires constant management. In this study, two items were diagnosed and analyzed in order to derive the optimal operation method of flare system. First, to detect the cause of the rise in flame height, the acoustic leak detector was used to check gas leaks in safety valves and pressure control valves. Second, to identify the cause of flame instability, the pulsation phenomenon was diagnosed through the CFD simulation and modeling experiments of the sealing drum. By confirming the leak at 4.3% of the safety valve and 10% of the pressure control valve, the cause of abnormal sparking was derived. The information presented in this study can be easily applied to any company that has a flare system, and is expected to prevent complaints and product loss.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.