• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.195-198
• /
• 2009

Recently, research in building up semantic web for exchanging information and knowledge is active. To make use of video contents as knowledge on semantic web, semantic-based retrieval should be preceded. At present, retrieval based on consentaneity between metadata and keyword is common used. In this paper, I propose ontolgy establishment which enlarge user participation and add usefulness value and history information. This will facilitate semantic retrieval as well as use of video contents by using collective Intelligence. The proposed ontology schema will allow semantic-based retrieval of video contents on semantic web get higher recall compared to current way of retrieval. Moreover it enables you to make use of various video contents as knowledge.

• Journal of the Korean Society of Radiology
• /
• v.82 no.6
• /
• pp.1570-1574
• /
• 2021

Post-partum galactocele is a common benign disease among breastfeeding women, whereas retromammary and peri-implant galactocele are relatively rare conditions. Herein, a 34-year-old, 1 month-postpartum female, who had augmentation mammoplasty and a 1-month history of breast pump use, presented with left breast enlargement for 2 weeks. An initial left breast US revealed hyperechoic peri-implant fluid collection. Additional US-guided fine needle aspiration was done using a 21G-needle, draining the milk component in the process, and cytologic results revealed numerous crystals, suggestive of galactocele. Various diseases, especially breast implant-associated anaplastic large cell lymphoma, can cause peri-implant fluid collection in an augmented breast. Thus, correlating imaging features with clinical information and cytologic analysis plays an important role in appropriate management.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.129-135
• /
• 2016

There are many visual enhancement devices for people with low vision. However, almost conventional devices have been simple magnifying and high cost. The symptoms of people with low vision are very variety. It needs to control of image magnifying, brightness, and contrast to improve the visuality. We developed a portable microdisplay driver and device for visual enhancement. This device based on our suggested four methods such as image magnifying, specific color control, BLU brightness control, and visual axis control using a prism. The basic clinical experiments of the proposed Head Mounted Visual Enhancement Device (HMVED) have been performed. The results show beneficiary effects compared with conventional devices, and improve the life quality on people with low vision on account of low weight, low cost, and easy portability.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.4
• /
• pp.562-569
• /
• 2010

This paper analyzes the problems that occurred in the magnification process for a fine input image and investigates a method to improve the blurring of magnified image. This paper applies a curve interpolation algorithm in CAD/CAM for the same test images with the existing image algorithm in order to improve the blurring of magnified image. As a result, the nearest neighbor interpolation, which is the most frequently applied algorithm for the existing image interpolation algorithm, shows that the identification of a magnified image is not possible. Therefore, this study examines an interpolation of gray-level data by applying a low-pass spatial filter and verifies that a bilinear interpolation presents a lack of property that accentuates the boundary of the image where the image is largely changed. The periodic B-spline interpolation algorithm used for curve interpolation in CAD/CAM can remove the blurring but shows a problem of obscuration, and the Ferguson' curve interpolation algorithm shows a more sharpened image than that of the periodic B-spline algorithm. For the future study, hereafter, this study will develop an interpolation algorithm that has an excellent improvement for the boundary of the image and continuous and flexible property by using the NURBS, Ferguson' complex surface, and Bezier surface used in CAD/CAM engineering based on the results of this study.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.15-18
• /
• 2023

UAV는 군사용을 처음 시작으로 근래에 취미용 드론의 급격한 성장과 더불어 최근 기후변화, 교통혼잡, 범죄 예방 등 여러 사회 문제 해결을 위한 드론의 필요성이 증가함에 따라 건설, 교통, 농업, 에너지, 엔터테인먼트 등 다양한 산업과 여러 사회 서비스로 그 필요성이 확대되고 있다. 본 연구는 이러한 사회적 흐름에 따라 인공지능 기술을 통한 드론의 활용성을 확대하고 GPS 수신이 안 되는 환경에서 딥러닝 객체 탐지 모델을 활용한 자율 착륙을 연구를 목표로 한다. GPS 신호는 실내와 같은 환경 혹은 지하, 교량 아래, 산속 등과 같은 곳에서는 수신이 어렵다. 이를 극복하고자 GPS 신호수신이 어려운 지역에서 GPS 수신기를 통해 받는 위치 정보 대신 드론에 장착된 카메라를 통해 전달받는 영상에서 착륙할 지점을 인식하고 카메라를 통해 받는 영상 정보만 이용하여 목표지점으로 하강하는 방식으로 자율 착륙을 유도한다. 딥러닝 중 경량화 모델을 활용하여 소형 드론에서 실시간으로 착륙 지점을 감지하기 위해 최적화 과정을 진행해 실시간 자율 착륙이 가능하게 하였다. 본 연구를 통해 드론의 착륙에 있어 GPS 수신기와 사람의 조종에 대한 의존도를 낮출 수 있을 것으로 기대한다.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.26-32
• /
• 2024

Recently, various video resolution formats have emerged, and digital devices have built in dedicated scaler chips to support them by enlarging or reducing the resolution of input videos. Therefore, the performance and hardware size of scaler chips are important. In this paper, the combinatorial interpolation scaler algorithm proposed by Han is used to design the hardware using the line memory structure with dual-clock proposed by Han and Jung. The proposed hardware is capable of real-time processing in QHD environments, designed using Verilog, and validated using Xilinx's Vivado 2023.1. We also verify the performance of Han's proposed algorithm with a quantitative numerical evaluation of the proposed hardware.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.875-880
• /
• 2013

When we generate 3D video that provides immersive and realistic feeling to users, depth information of the scene is essential. Since the resolution of the depth map captured by a depth sensor is lower than of the color image, we need to upsample the low-resolution depth map for high-resolution 3D video generation. In this paper, we propose a depth upsampling method using depth-discontinuity information. Using the high-resolution color image and the low-resolution depth map, we detect depth-discontinuity regions. Then, we define an energy function for the depth map upsampling and optimize it using the belief propagation method. Experimental results show that the proposed method outperforms other depth upsampling methods in terms of the bad pixel rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2280-2286
• /
• 2012

In this paper, we propose a novel nonlinear 3D image correlator using a fast computational integral imaging reconstruction (CIIR) method. In order to implement the fast CIIR method, the magnification process was eliminated. In the proposed correlator, elemental images of the reference and target objects are picked up by lenslet arrays. Using these elemental images, reference and target plane images are reconstructed on the output plane by means of the proposed fast CIIR method. Then, through nonlinear cross-correlations between the reconstructed reference and the target plane images, the pattern recognition can be performed from the correlation outputs. Nonlinear correlation operation can improve the recognition of 3D objects. To show the feasibility of the proposed method, some preliminary experiments are carried out and the results are presented by comparing the conventional method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.487-492
• /
• 2018

Recently, various applications for image processing have been ported to the mobile environment due to the expansion of the image shooting on the mobile device. However, in the case of extracting the image foreground, which is one of the most important functions of image synthesis, is difficult since it needs complex calculation. In this paper, we propose an video synthesis technique that can divide images captured by mobile devices into foreground / background and combine them in real time on target images. Considering the characteristics of mobile shooting, our system can extract automatically foreground of input video that contains weak motion when shooting. Using SIMD and GPGPU-based acceleration algorithms, SD-quality images can be processed on mobile in real time.

• Korean Journal of Remote Sensing
• /
• v.24 no.6
• /
• pp.591-603
• /
• 2008

Satellite performance can be evaluated by image quality. MTF(Modulation Transfer Fuction), SNR(Signal To Noise Ratio), GSD(Ground Sample Distance) etc. are important bias parameters to analyze image quality. It is necessary to estimate quality of satellite image in design stage. In this paper, the simulating method of satellite image quality, considering design, manufacturing, and operation, is proposed. The proposed method shall be used to estimate and restore quality of satellite image.