• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11
• /
• pp.3333-3340
• /
• 2000

Recently, Requnremeni for video data have been increased rapidly by high progress of both hardware and cornpression technique. Because digital video data are unformed and mass capacity, it needs various retrieval techniquesjust as contednt-based rehieval Superimposed-caption ina digital video can help us to analyze the video story easier and be used as indexing information for many retrieval techniques In this research we propose a new method that segments the caption as analyzing texture eature of caption regions in each video frame, and that extracts the accurate scope of superimposed-caption frame and its key regions and color by measunng cominuity of caption regions between frames

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.5 no.4
• /
• pp.19-26
• /
• 2002

This is a brief report on the development of a system which provides fishing vessels with a real-time key information that can direct to regions of high fish density. Water temperature and Plankton distribution are the base parameters and various public information have been examined and summarized. The suface water temperature can be obtained from NOAA's high resolution infrared data base and the vertical water temperature can be obtained from TAO/TRITON's buoy near the equator and ARGOS's drifting buoy covering wider Pacific ocean. MODIS's data is also utilized for sea color information. A model data format is proposed and a few examples are demonstrated.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.11
• /
• pp.9-15
• /
• 2011

In this paper, we design and implement of gate management system by face recognition using smart phone. We investigate various algorithms for face recognition on smart phones. First step in any face recognition system is face detection. We investigated algorithms like color segmentation, template matching etc. for face detection, and Eigen & Fisher face for face recognition. The algorithms have been first profiled in MATLAB and then implemented on the Android phone. While implementing the algorithms, we made a tradeoff between accuracy and computational complexity of the algorithm mainly because we are implementing the face recognition system on a smart phone with limited hardware capabilities.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.12
• /
• pp.3711-3717
• /
• 2010

Four orange-red phosphorescent Ir(III) complexes were designed and synthesized based on the benzoylphenylpyridine ligand with a fluorine substituent. Multilayered OLEDs with the device structure, ITO/2-TNATA/NPB/CBP : 8% Ir(III) complexes/BCP/Liq/Al, were fabricated using these complexes as dopant materials. All the devices exhibited orange-red electroluminescence and their electroluminescent properties were quite sensitive to the structural features of the dopants in the emitting layers. Among these, the maximum luminance ($14700\;cd/m^2$ at 14.0 V) was observed in the device containing Ir(III) complex 1 as the dopant. In addition, its luminous, power and quantum efficiency were 11.7 cd/A, 3.88 lm/W and 9.58% at $20\;mA/cm^2$, respectively. The peak wavelength of electroluminescence was 606 nm with CIE coordinates of (0.61, 0.38) at 12.0 V. The device also showed stable color chromaticity with various voltages.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.3
• /
• pp.97-124
• /
• 2012

This paper analyzes qualitatively the stereo 3D content factors causing viewer's discomfort. For this, we perform a subjective test that each subject strokes a specific key whenever he (she) feels discomfort during watching a stereo 3D contents. Also we extract the data for the factors in the 3D contents to obtain their quantitative values and the amounts of the temporal changes. Those two sets of data are used to analyze the contents to find the factors which cause viewer's discomfort. The factors to be considered are the amount and the frequency of the disparity changes, story of the contents, situation or environments of a scene, movement and the position of the camera, color and luminance information as well as disparities themselves. We analyse the various strong and weak factors and their composites to find how much discomfort each factor or composite causes. We also show the situations and their related factors that causes less discomfort than the amount of their disparities.

• Korean Journal of Optics and Photonics
• /
• v.28 no.3
• /
• pp.103-107
• /
• 2017

In this paper, we have designed an optical measurement system for authenticity of paintings. Using a simple and compact optical measurement system, the surface characteristics of paintings could be measured, and we obtained information about paintings. First, the paintings that were painted in various colors could give characteristic information on the color of paintings. Second, tomographic information about the surface of a painting could be obtained, using a line laser. To assess the reliability of the optical measurement system, forgeries looking like the originals were created, and we could distinguish the originals from the forgeries through experiment. Thus, we could obtain data about the paintings and create a numerical database.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.653-654
• /
• 2022

Recently, technology development using artificial intelligence (AI) is being conducted in various fields. It is being used in many areas, from a personalized recommendation system for general personal taste to the development of application technology that meets a specific purpose. In this study, for adult detection, we propose a method for detecting adults in elementary schools where many elementary school students live. Clothing color, pattern, style, or physical size are used as factors to differentiate between adults and children, and through this, it will be possible to quickly detect adults or unauthorized adults who break into elementary schools and use them in the pre-recognition system.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2023

Open surface water body extraction is gaining popularity in recent years due to its versatile applications. Multiple techniques are used for water detection based on applications. Different applications of Radar as LADAR, Ground-penetrating, synthetic aperture, and sounding radars are used to detect water. Shortwave infrared, thermal, optical, and multi-spectral sensors are widely used to detect water bodies. A stereo camera is another way to detect water and different methods are applied to the images of stereo cameras such as deep learning, machine learning, polarization, color variations, and descriptors are used to segment water and no water areas. The Satellite is also used at a high level to get water imagery and the captured imagery is processed using various methods such as features extraction, thresholding, entropy-based, and machine learning to find water on the surface. In this paper, we have summarized all the available methods to detect water areas. The main focus of this survey is on water detection especially in small patches or in small areas. The second aim of this survey is to detect water hazards for unmanned vehicles and off-sure navigation.

• Archives of design research
• /
• v.15 no.4
• /
• pp.111-120
• /
• 2002

Folk paintings influence the lifestyle of the general public, and is visible practical communication presenting emotion, feelings and phenomenon through various functions and aesthetic molding specificity. Illustration as a medium for conveying information in modern society is time communication forming time circumstance based on a creative image, becoming an importance in the means of molding an active information society. Folk paintings and illustration express the subject of various kinds of stories of surroundings of daily lives ironically, humorously and symbolically, convey it in an accurate and detailed way in the various use of color and shape representation, and have a similar specificity as the general public's art influencing the society, culture, and environment, the general public's emotion and feelings of that time. The current research is to suggest the possibility and direction of Korean image representation in illustration by analyzing folk painting and illustration characters based on social, cultural function and role and molding specificity.

• 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.