• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.645-655
• /
• 2021

The aim of this study was to understand the psychological characteristics of nursing students, using an Enneagram questionnaire and drawing a free mandala. The subjects were 127 students from a nursing university in South Chungcheong Province. The data were collected from October 16 to November 13, 2020 and analyzed using χ² test, t-test, ANOVA, and Scheffé test with SPSS ver.25.0. Mandala analysis method and evaluation criteria of Mandala referred to the Fincher(1991), Kellogg(1977), and Jeong Yeo-ju(2001), and a total of three people discussed the adequacy and clarity of the analysis criteria composition system. The findings of this study can be summarized as follows. As a result of the study, there were significant differences between the thinking type in the case of overwhelming color, the instinct type in the case of light and dark, and the thinking type and emotion type in the case of the Great mandala. Through the results of this study, it is necessary to understand one's personality type in the nursing education process from the freshman year, identify strengths and weaknesses, and provide a process that can be supplemented.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.4
• /
• pp.105-118
• /
• 2006

The purpose of this research is twofold. The first is to develop the measures for evaluating performance of fingerprint sensor modules quantitatively and objectively. The second is to present the methodology for evaluating compatibilities among disparate fingerprint sensors. This paper focuses on the performance evaluation not of fingerprint authentication algorithm but of fingerprint sensors. Presented in this paper are several indicators and their measuring schemes such as the actual resolution of fingerprint images, the level of distortion by horizontal and vertical resolutions of fingerprint image, the intensity distribution for various illuminating conditions. Nine commercial sensor modules have been tested and the test results are expressed by using 95% confidence interval based on 50 acquired fingerprint images. The experimental results are compared with the manufacturer's sensor specification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.865-871
• /
• 2022

In this paper, we propose a method of extracting prostate region using morphological characteristics of ultra-sonic image of prostate. In the first step of the proposed method, the edge area of the prostate image is extracted. The histogram of ultra-sonic image is used to extract base objects to detect the upper edge of prostate region by altering the contrast of the image, then, the lower edges of the extracted base objects are connected by using monotone cubic spline interpolation to extract the upper edge. Step 2, Otsu's binarization is applied to the region under the extracted upper edge of the prostate ultra-sonic image to extract the lower edge of prostate. In the last step, the upper and the lower edges are connected to extract prostate region and by comparing the extracted region of prostate with the one measured manually, the result showed that the morphological characteristics of prostate in ultrasonic image can be utilized to extract the prostate region.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.61-70
• /
• 2022

Connectivity and knowledge are the main keywords of the IoT. In this paper, I analyzed how the two civilizations, Christianity and Islam, were connected through Mughal paintings and what result they have brought in the spread of knowledge. For that, I analyzed literature as well as paintings of those days. In terms of theme matter, Western painting was used as a means of strengthening the royal authority of the Mughal Emperor. In terms of style, perspective and shading from the Western Paintings began to be used in Mughal painting. Later, Christian symbols and themes were linked to absolute power of kingship, and further utilized them to develop into the concept of kingship = spirituality = divinity, creating an original art style that was unprecedented in the history of world painting. By analyzing the two disparate cultures in terms of 'connectivity' and 'knowledge' of the Internet of Things, such research could serve as a platform for future humanities research on the Internet of Things.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.457-462
• /
• 2023

Director Yoon Jong-bin's new series <The Accidental Narco, Narco-Saints> was streamed through Netflix in 2022 and ranked first in the series rankings. <The Accidental Narco, Narco-Saints> continues the genealogy of male narratives in Korean society that director Yoon Jong-bin has pursued for a long time. In <The Accidental Narco, Narco-Saints>, the main characters choose the path of the diaspora to escape Korean society and seek survival in a foreign country. The two male protagonists of <The Accidental Narco, Narco-Saints> are set up in a hostile relationship, but they have one thing in common: they basically pursue money to "survive". They chose the diaspora to avoid the tyranny of public power in Korean society in the 1980s and 1990s, but Republic of Suriname was the worst place where private violence and public power were completely callused. In there, one becomes a drug lord and the other chooses to act for his duty to Korea. These two different choices can be said to be examples of the light and shade of the diaspora. In <The Accidental Narco, Narco-Saints>, director Yoon Jong-bin inherited the themes of 'family' and 'violence' from previous works, while expanding the geographical area of Korean male narratives he had been exploring.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.61-71
• /
• 2009

Vehicle license plate is the only way to check the registrated information of a vehicle. Many works have been devoted to the vision system of recognizing the license plate, which has been widely used to control an illegal parking. However, it is difficult to correctly segment characters on the license plate since an illumination is affected by a weather change and a neighboring obstacles. This paper proposes a robust method of segmenting the character of the license plate on irregular illumination condition. The proposed method enhance the contrast of license plate images using the Chi-Square probability density function. For segmenting characters on the license plate, binary images with the high quality are gained by applying the adaptive threshold. Preprocessing and labeling algorithm are used to eliminate noises existing during the whole segmentation process. Finally, profiling method is applied to segment characters on license plate from binary images.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.151-151
• /
• 2020

표면영상유속측정법은 영상을 이용한 비접촉식 유속 측정 방법으로 카메라 외에 별도로 고가의 장비를 구매할 필요가 없을 뿐 아니라 현장 상황을 영상으로 확인할 수 있기 때문에 현장조사인력이 필요 없어 경제적이고, 안전하다는 장점을 갖고 있는 하천 유속 측정 방법이다. 표면영상유속측정법은 일반적으로 상호상관법을 이용하여 수표면을 촬영한 연속된 두 영상에서 입자군의 명암값 분포를 계산하여 입자군의 변위를 계산하고 이를 두 영상 사이의 시간 간격으로 나누어 입자군의 이동 속도를 산정하는 방법이다. 따라서 표면영상유속측정법으로 산정한 유속의 정확도를 높이기 위해서는 영상 내 두 입자군의 변위를 정확하게 계산하는 것이 무엇보다 중요하다. 즉, 분석하고자 하는 영상의 물리거리를 정확하게 계산할 수 있어야 한다. 카메라를 이용하여 실제 하천 영상을 촬영한 영상은 카메라 렌즈에 의한 왜곡이 필연적으로 발생하게 되고 이는 영상 내의 변위 산정 시에도 영향을 미친다. 특히 드론을 활용하여 넓은 하천 영역을 촬영할 경우 카메라 렌즈에 의한 왜곡은 실제 물리 변위 계산 정확도에 큰 영향을 미치게 된다. 이에 본 연구에서는 카메라 왜곡이 영상 내 변위 산정 결과의 정확도에 미치는 영향을 분석하였다. 연구 결과 카메라 렌즈 왜곡은 영상 중심에서 방사방향으로 점점 크게 발생하고 왜곡 정도는 비선형적으로 나타났으며, 변위 측정 오차는 영상의 중앙부에서는 거의 차이가 없었으며, 영상 외곽부에서 최대 오차가 발생하는 것으로 나타났다. 그리고 카메라 렌즈 왜곡 보정을 실시하게 되면 영상 전체적으로 변위측정 오차는 모두 제거할 수 있는 것으로 확인하였다. 따라서 카메라 렌즈 왜곡 보정을 실시하여 표면영상유속 측정 결과의 정확도를 개선할 수 있는 것으로 나타났다. 향후 카메라 렌즈 왜곡 보정을 실시한다면 하천의 표면유속을 보다 정확하게 측정할 수 있을 것으로 기대한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.2-5
• /
• 2022

Human organs in the body have a complex structure, and in particular, the small intestine is about 7m long, so endoscopy is not easy and the risk of endoscopy is high. Currently, the test is performed with a capsule endoscope, and the test time is very long. The doctor connects the removed storage device to the computer to store the patient's capsule endoscope image and reads it using a program, but the capsule endoscope test results in a long image length, which takes a lot of time to read. In addition, in the case of the small intestine, there are many curves due to villi, so the occlusion area or light and shade of the image are clearly visible during the examination, and there may be cases where lesions and abnormal signs are missed during the examination. In this paper, we provide a method of assisting small intestine capsule endoscopic lesion examination using artificial neural networks to shorten the doctor's image reading time and improve diagnostic reliability.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.859-866
• /
• 2023

This paper focuses on configuring a user-friendly system of LED systems by applying improvement measures such as gamma correction, non-flicker, and driving noise removal using MCUs and LED drivers. As a result of the experiment, the 22kHz PWM mode of the LED driver generated noise outside the audible frequency range, making it practically imperceptible to users. The appropriate pull-up resistor values within the normal operating delay ratio of 5% were found to be 1kΩ to 10kΩ for the 3kHz PWM mode and 1kΩ to 2kΩ for the 22kHz PWM mode. In addition, gamma correction can be optimized for nonlinear human visual systems to express accurate contrast and as a result, it is expected to develop an LED system that can be expressed more naturally and accurately than conventional LED systems and improve users' visual experience.