• Title/Summary/Keyword: Landmark information

Search Result 173, Processing Time 0.024 seconds

Design of CNN-based Gastrointestinal Landmark Classifier for Tracking the Gastrointestinal Location (캡슐내시경의 위치추적을 위한 CNN 기반 위장관 랜드마크 분류기 설계)

  • Jang, Hyeon-Woong;Lim, Chang-Nam;Park, Ye-Seul;Lee, Kwang-Jae;Lee, Jung-Won
    • Annual Conference of KIPS
    • /
    • 2019.10a
    • /
    • pp.1019-1022
    • /
    • 2019
  • 최근의 영상 처리 분야는 딥러닝 기법들의 성능이 입증됨에 따라 다양한 분야에서 이와 같은 기법들을 활용해 영상에 대한 분류, 분석, 검출 등을 수행하려는 시도가 활발하다. 그중에서도 의료 진단 보조 역할을 할 수 있는 의료 영상 분석 소프트웨어에 대한 기대가 증가하고 있는데, 본 연구에서는 캡슐내시경 영상에 주목하였다. 캡슐내시경은 주로 소장 촬영을 목표로 하며 식도부터 대장까지 약 8~10시간 동안 촬영된다. 이로 인해 CT, MR, X-ray와 같은 다른 의료 영상과 다르게 하나의 데이터 셋이 10~15만 장의 이미지를 갖는다. 일반적으로 캡슐내시경 영상을 판독하는 순서는 위장관 교차점(Z-Line, 유문판, 회맹판)을 기준으로 위장관 랜드마크(식도, 위, 소장, 대장)를 구분한 뒤, 각 랜드마크 별로 병변 정보를 찾아내는 방식이다. 그러나 워낙 방대한 영상 데이터를 가지기 때문에 의사 혹은 의료 전문가가 영상을 판독하는데 많은 시간과 노력이 소모되고 있다. 본 논문의 목적은 캡슐내시경 영상의 판독에서 모든 환자에 대해 공통으로 수행되고, 판독하는 데 많은 시간을 차지하는 위장관 랜드마크를 찾는 것에 있다. 이를 위해, 위장관 랜드마크를 식별할 수 있는 CNN 학습 모델을 설계하였으며, 더욱 효과적인 학습을 위해 전처리 과정으로 학습에 방해가 되는 학습 노이즈 영상들을 제거하고 위장관 랜드마크 별 특징 분석을 진행하였다. 총 8명의 환자 데이터를 가지고 학습된 모델에 대해 평가 및 검증을 진행하였는데, 무작위로 환자 데이터를 샘플링하여 학습한 모델을 평가한 결과, 평균 정확도가 95% 가 확인되었으며 개별 환자별로 교차 검증 방식을 진행한 결과 평균 정확도 67% 가 확인되었다.

Appropriateness of Selecting the Chest Compression Site by Lay-Persons: Compared to the center of the lower half of the breastbone and above the two fingers on solar plexus

  • Choi, Sung-Soo;Han, Seung-Tae;Yun, Seong-Woo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.25 no.12
    • /
    • pp.211-217
    • /
    • 2020
  • This study is to find out the effectiveness by adult CPR method of a single rescuer. For patients with acute cardiac arrest, CPR is the only first aid, and chest compression is the most important of these techniques. The subjects of this study were freshman, 120 subjects who did not learn CPR, and for data analysis, the SPSS 22.0 Version was used. The accuracy of chest compression site selection was significantly higher in the upper part of the two fingers in the pit of the stomach(p<.001), and the ease was also high(p<.001). In the case of the general public, they select the chest compression area easily and quickly, it turns out that it is easier to designate the landmark toward the pit of the stomach. In the future, through various job groups, research to select the chest compression site is needed, and additional studies should be conducted to confirm the maintenance and accuracy during chest compression.

A Method of Dog Recognition using Nose Print and Landmarks

  • Kwak, Ho-Young;Yun, Young-Min;Chang, Jin-Wook;Song, Woo Jin;Kim, Soo Kyun
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.2
    • /
    • pp.99-106
    • /
    • 2022
  • In this paper, We propose a method for identifying objects by setting inscriptions and landmarks of dogs. The phenomenon of abandoning dogs is on the rise, and the number of abandoned individuals is also rapidly increasing. These abandoned dogs are becoming wild animals, causing a lot of damage to people's daily life, causing serious problems. As a solution to this problem, the animal registration system is being implemented, but there is a phenomenon that some dog owners avoid the registration method that inserts a chip, so the complete registration system is not settled. When registering a dog, removing the avoidance of dog owners will help establish the companion animal registration system. In this paper, we present a technique to identify objects by setting inscriptions and landmarks of dogs so that dog owners can register their dogs in a friendly way to eliminate this avoidance phenomenon.

Non-contact Input Method based on Face Recognition and Pyautogui Mouse Control (얼굴 인식과 Pyautogui 마우스 제어 기반의 비접촉식 입력 기법)

  • Park, Sung-jin;Shin, Ye-eun;Lee, Byung-joon;Oh, Ha-young
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.9
    • /
    • pp.1279-1292
    • /
    • 2022
  • This study proposes a non-contact input method based on face recognition and Pyautogui mouse control as a system that can help users who have difficulty using input devices such as conventional mouse due to physical discomfort. This study includes features that help web surfing more conveniently, especially screen zoom, scroll function, and also solves the problem of eye fatigue, which has been suggested as a limitation in existing non-contact input systems. In addition, various set values can be adjusted in consideration of individual physical differences and Internet usage habits. Furthermore, no high-performance CPU or GPU environment is required, and no separate tracker devices or high-performance cameras are required. Through these studies, we intended to contribute to the realization of barrier-free access by increasing the web accessibility of the disabled and the elderly who find it difficult to use web content.

Applications of a Deep Neural Network to Illustration Art Style Design of City Architectural

  • Yue Wang;Jia-Wei Zhao;Ming-Yue Zheng;Ming-Yu Li;Xue Sun;Hao Liu;Zhen Liu
    • Journal of Information Processing Systems
    • /
    • v.20 no.1
    • /
    • pp.53-66
    • /
    • 2024
  • With the continuous advancement of computer technology, deep learning models have emerged as innovative tools in shaping various aspects of architectural design. Recognizing the distinctive perspective of children, which differs significantly from that of adults, this paper contends that conventional standards may not always be the most suitable approach in designing urban structures tailored for children. The primary objective of this study is to leverage neural style networks within the design process, specifically adopting the artistic viewpoint found in children's illustrations. By combining the aesthetic paradigm of urban architecture with inspiration drawn from children's aesthetic preferences, the aim is to unearth more creative and subversive aesthetics that challenge traditional norms. The selected context for exploration is the landmark buildings in Qingdao City, Shandong Province, China. Employing the neural style network, the study uses architectural elements of the chosen buildings as content images while preserving their inherent characteristics. The process involves artistic stylization inspired by classic children's illustrations and images from children's picture books. Acting as a conduit for deep learning technology, the research delves into the prospect of seamlessly integrating architectural design styles with the imaginative world of children's illustrations. The outcomes aim to provide fresh perspectives and effective support for the artistic design of contemporary urban buildings.

A Study on the Operation Direction of the Specialized Library Based on the Local Environment: Focusing on the Construction of County A Library (지역 환경 기반의 특성화 도서관 운영 방향에 관한 연구: A군 도서관 건립을 중심으로)

  • Bo-il Kim;Hong-Ryul Kim
    • Journal of the Korean Society for information Management
    • /
    • v.41 no.1
    • /
    • pp.59-83
    • /
    • 2024
  • The directions of recent library construction and operation reflect people's changed lifestyle and suggest innovative spaces specialized on the basis of the local environment. Hence, as the goals of the operation of (tentatively named) Songdaeso Library to be constructed within the Hantangang River UNESCO Global Geopark, this study proposes 'acting as complex cultural facilities,' 'operating stay-type reading culture space which is a shrine for workcation,' and 'acting as the landmark of A-gun (郡, county).' And this study works out strategies for its operation, which includes 'securing the validity of the construction of (tentatively named) Songdaeso Library,' 'linking to library policy as the driving force behind its operation,' and 'demonstrating the necessity for the existence of the library arising from the operation of the geological specialized library through landscape architecture.' It also presents concomitant operating plans, which are categorized into plans for manpower, library books, services, and budget.

A Study on the Establishment of Basic Policy for the Operation of Sejong City Library (세종시립도서관의 운영 기본 정책 수립에 관한 연구)

  • Kwak, Seung-Jin;Noh, Younghee;Oh, Sanghee;Kim, Jeong-Taek;Shin, Youngji
    • Journal of Korean Library and Information Science Society
    • /
    • v.51 no.4
    • /
    • pp.157-183
    • /
    • 2020
  • This study was a basic study for the establishment of basic policies for the operation of Sejong City Library. It was intended to establish and operate the functions and roles of Sejong City Library by conducting a general survey on the current status, user demand, expert opinion, and librarian opinion survey. As a result, the Sejong City Library is the representative library of Sejong Special Self-Governing City, which oversees all public and small libraries in Sejong Special Self-Governing City and carries out support and cooperation projects, and should improve the development of the local community and the quality of life of local residents by providing more convenient and equal access to provide information services and cultural programs. Second, apart from providing library services to local residents in Sejong Special Self-Governing City, the functions of the Sejong Special Self-Governing City's representative library and hub library, knowledge and information center, lifelong education center, social and cultural center, leisure culture center, leisure and convenience center, and furthermore, it should function as a policy information support center. Finally, in order to enhance the brand value of Sejong City Library, the Sejong City Library as a landmark in Sejong area, the Sejong City Library as an art and cultural hub in Sejong area, the Sejong City Library as a complex cultural space in Sejong area, and the Sejong City Library as a center for Sejong Studies were proposed.

Determination of the Elbow Transverse Joint Using the Helical Axis Concept and its Application to the Development of a Kinematic Arm Model (나선축 개념을 이용한 팔꿈치 관절의 3차원 회전축 측정과 측정 결과를 반영한 인체 팔 모델의 개발)

  • Woo, Bum-Young;Jung, Eui-S.;Yun, Myung-Hwan
    • Journal of Korean Institute of Industrial Engineers
    • /
    • v.26 no.1
    • /
    • pp.73-80
    • /
    • 2000
  • To determine the exact direction and location of the human joint in motion is crucial in developing a more accurate human model and producing a more fitting artificial joint. There have been several reports on the biomechanical analysis of the joint to determine the anatomy and movement of joints. However, all the previous researches were made in vitro study, that is, they investigated the passive movement of the joint from cadavers and the suggested location of the joint axis was difficult to make practical applications due to the lack of the direction of joint axis. Also, in many biomechanical models, each joint axis is assumed to lie horizontally or vertically to the adjacent links. Such an assumption causes inherent inaccuracy. In this study, the direction and location of the transverse elbow axis was obtained with respect to the global coordinate system whose origin is on the lateral epicondyle of the humerus. The suggested result based on the global coordinate system lying on the external landmark will be helpful to understand the information of the axis and to make an application. From the experiments conducted for five subjects, the direction and location of the elbow transverse joint was determined for each subject by the helical axis method. A statistical validation was also performed to confirm the result. Finally, the result was applied to develop a simple elbow model which is a part of the kinematic arm model. The simple elbow movement model was developed to validate the significance of the result and the kinematic arm model was able to describe the geometry of any complex linkage system. As a result, the errors incurred from the proposed model were significantly reduced when compared to the ones from the previous approach.

  • PDF

A Study of Methods to Foster Manhole Cover Design -Focused on manhole cover designs in 'Streets of History and Culture'-

  • Lee Cho-Rog;Yoon Jong-Young
    • Archives of design research
    • /
    • v.19 no.3 s.65
    • /
    • pp.167-182
    • /
    • 2006
  • From 1998 Seoul city is being rebuilt for 'the city which people want to go around on foot'. Many streets only for cars have been transformed for pedestrians. In addition to that streets are built not only just to pass by, but also enjoy themselves, so 8 Streets in Seoul have been redecorated as 'Streets of History and Culture'. These Streets are chosen because they have their own unique history or culture, so they are remodeled with lightings, exhibition pavilions or sign postings etc except manhole covers. Even these 8 streets have manhole covers; they are not particular, just same as like other streets. For most streets manhole cover is an essential component of them, but it is mostly omitted to be designed in particular. For the most time some of the standard manhole covers are installed in a street. Taking a look at manholes in Minneapolis city, they inform visitors what the landmark, landscape, symbol, representative flower or tree of the city is. Sometimes they are designed by famous artists and become art which all pedestrian can enjoy. If manhole covers in 'the streets of history and culture' are designed to represent its history or culture, visitors will get information about there easily and enjoy their design. To foster manhole cover designs, the government office should co-work with professional designers or design societies and encourage people to spend a certain amount of the construction cost to design manhole covers. At school designing manhole cover can be handled in an art class and besides can have a class in the field, streets to observe manhole cover designs. Getting more concern of manhole cover design, competitions and exhibitions are able to be held.

  • PDF

A Basic Study on the Space Organization and Forming Characteristics of the Guggenheim Museums based on Emotional Approach - Focused on Frank L. Wright & Frank O. Gehry′s Works - (감성적 접근에 의한 구겐하임 뮤지엄의 공간구성과 조형특성에 관한 기초적 연구 - 라이트와 게리 작품 비교를 중심으로 -)

  • 서수경
    • Korean Institute of Interior Design Journal
    • /
    • v.13 no.5
    • /
    • pp.82-89
    • /
    • 2004
  • Today, people are bombarded with information, high-technology and multimedia. With that in mind, museum can no longer attract visitor with traditional concept, so it must find some solution or stimulation to attract their attention back. New museum is becoming a experimental space for new culture, new education, and most of all a place to fulfill one's satisfaction of life. Over the past centuries, Guggenheim Foundation has done a great job in providing place for art and place to get emotional stimulation. Out of all of their museums, Frank L. Wright's Solomon R. Guggenheim in New York and frank O. Gehry's Guggenheim Museum in Bilbao had most unique character yet share similar feature to be recognized as the architectural landmark of the 20th & 21st century Although there are close to 50 years of gap between two museums, their unique, attractive, site-specific, emotional value comes from the two most innovative architect of the past and present century. For Wright the Guggenheim was his last project but it had one of the greatest impact on his career and for Gehry the museum gave him confidence that anything is possible. This study will focus on the spatial organization as well as the architectural formation of both museum to compare and analyze. The goal of the research is to give fundamental data which will reveal emotional elements as well as concepts from each work. The content of this research will mainly focused on their architectural philosophy and it will reveal their concept on human emotion as well as the characteristics of the spatial organization. The result of the study will be a valuable reference for people designing art & cultural facilities in the future.