• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.232-234
• /
• 2021

최근 휴먼-컴퓨터 인터페이스, 가상현식, 증강현실, 지능형 자동차등에서 얼굴표정 인식에 대한 연구가 활발히 진행되고 있다. 얼굴표정인식 연구는 대부분 맨얼굴을 대상으로 하고 있지만 최근 코로나-19로 인해 마스크 착용한 사람들이 많아지면서, 마스크를 착용했을 때의 표정인식에 대한 필요성이 증가하고 있다. 본 논문은 마스크를 착용했을 때에도 실시간으로 표정 분류가 가능한 시스템개발을 목표로 구동에 필요한 알고리즘을 조사했고, 그 중 Tiny-YOLOv3와 ResNet50 알고리즘을 이용하기로 했다. 얼굴과 표정 데이터셋 등에서 모은 이미지 데이터를 사용하여 실행해 보고 그 적절성 및 성능에 대해 평가해 보았다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.807-809
• /
• 2020

기존의 CCTV 관리 체계는 사건·사고에 대한 신속한 조치가 불가능하고 정황 파악이나 증거자료 확보 등 사후조치의 성격이 강하다. 본 논문에서는 Mask R-CNN(Regions with CNN)을 이용하여 CCTV가 읽어 들이는 객체가 응급상황인지 판단하는 방법을 제시한다. 사람으로 인식되는 영역을 다층 퍼셉트론(MLP, Multi-Layer Perceptron)으로 학습시켜 해당 대상이 처한 상황을 인지하고 응급상황으로 인식되는 상황이 지속될 경우 관리 모니터를 통해 사용자에게 알림을 준다. 본 연구를 통해 실시간 상호작용적인 CCTV 관리 체계를 구축하여 도움이 필요한 사람의 골든타임을 놓치지 않게 될 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.678-680
• /
• 2023

본 연구는 2022년 유네스코 인류무형유산 대표목록에 등재된 탈춤 동작을 디지털화하여 후속 세대에게 정보를 제공하는 것을 목적으로 한다. 데이터 수집은 국가무형문화제로 지정된 탈춤 단체 13개, 시도무형문화재 단체 5개에 소속된 무형문화재, 전승자 39명이 관성식 모션 캡처 장비를 착용하고, 8대의 카메라를 이용하여 수집하였다. 데이터 가공은 바운딩박스를 수행하였고, 탈춤동작 추정은 YOLO v8을 사용하였고 탈춤 동작 분류는 YOLO v8에 CNN모델을 결합하여 130개의 탈춤을 분류하였다. 연구결과, mAP-50은 0.953, mAP50-95는 0.596, Accuracy 70%를 달성하였다. 향후 학습용 데이터셋 구축량이 늘어나고, 데이터 품질이 개선된다면 탈춤 분류 성능은 더욱 개선될 것이라 기대한다.

• Journal of Korean society of Dental Hygiene
• /
• v.14 no.6
• /
• pp.831-838
• /
• 2014

Objectives: The purpose of the study was to investigate the perception and practice of the infection control by empowerment in the dental hygienists. Methods: A self-reported questionnaire was filled out by 200 dental hygienists in Gyeongbuk from January 3 to February 20, 2013. Data were analyzed by SPSS 12.0 program. The instrument of impowerment was adapted from Spreitzer and consisted of 12 questions including meaning(4 questions), competency(4 questions), self-decision(4 questions), and impact(4 questions). Impowerment was score by Likert 5 scale and higher score means higher impowerment. The instrument for hand washing recognition and practice was adapted from Kim and consisted of hand washing(5 questions), personal protective clothing management(5 questions), contaminated appliance management(3 questions), sterilization(3 questions), and infection control environment(8 questions). The empowerment instrument was score by Likert 5 scale and the mean was 3.83 points. Based on 3.83, infection control recognition and practice were divided into upper group and lower group. Cronbach alpha was 0.951 in empowerment, 0.931 in recognition, and 0.924 in practice in the study. Results: Based on the average points of 3.83, the groups were divided into two groups including upper group and lower group. The upper group showed higher score in hand washing than the lower group. In the protective clothing management, the upper group changed the mask at one-hour interval(p<0.001). Conclusions: In the viewpoint of empowerment, it had a significant influence on the perception and practice of the dental infection control in the dental hygienists.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.87-95
• /
• 2020

Generally, occupational safety and particularly construction safety is an intricate phenomenon. Industry professionals have devoted vital attention to enforcing Occupational Safety and Health (OHS) from the last three decades to enhance safety management in construction. Despite the efforts of the safety professionals and government agencies, current safety management still relies on manual inspections which are infrequent, time-consuming and prone to error. Extensive research has been carried out to deal with high fatality rates confronting by the construction industry. Sensor systems, visualization-based technologies, and tracking techniques have been deployed by researchers in the last decade. Recently in the construction industry, computer vision has attracted significant attention worldwide. However, the literature revealed the narrow scope of the computer vision technology for safety management, hence, broad scope research for safety monitoring is desired to attain a complete automatic job site monitoring. With this regard, the development of a broader scope computer vision-based risk recognition system for correlation detection between the construction entities is inevitable. For this purpose, a detailed analysis has been conducted and related rules which depict the correlations (positive and negative) between the construction entities were extracted. Deep learning supported Mask R-CNN algorithm is applied to train the model. As proof of concept, a prototype is developed based on real scenarios. The proposed approach is expected to enhance the effectiveness of safety inspection and reduce the encountered burden on safety managers. It is anticipated that this approach may enable a reduction in injuries and fatalities by implementing the exact relevant safety rules and will contribute to enhance the overall safety management and monitoring performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.5
• /
• pp.1033-1039
• /
• 2012

In this paper, a simple and robust algorithm is proposed for detecting each steel plate from a image which contains several steel plates. Steel plate is characterized by line edge, so line detection is a fundamental task for analyzing and understanding of steel plate images. To detect the line edge, the proposed algorithm uses the small eigenvalue analysis. The proposed approach scans an input edge image from the top left corner to the bottom right corner with a moving mask. A covariance matrix of a set of edge pixels over a connected region within the mask is determined and then the statistical and geometrical properties of the small eigenvalue of the matrix are explored for the purpose of straight line detection. Using the detected line edges, each plate is determined based on the directional information and the distance information of the line edges. The results of the experiments emphasize that the proposed algorithm detects each steel plate from a image effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1479-1486
• /
• 2011

In this paper, a simple and robust algorithm is proposed for detecting straight line segments in a steel plate image. Line detection from a steel plate image is a fundamental task for analyzing and understanding of the image. The proposed algorithm is based on small eigenvalue analysis. The proposed approach scans an input edge image from the top left comer to the bottom right comer with a moving mask. A covariance matrix of a set of edge pixels over a connected region within the mask is determined and then the statistical and geometrical properties of the small eigenvalue of the matrix are explored for the purpose of straight line detection. Before calculating the eigenvalue, each line segment is separated from the edge image where several line segments are overlapped to increase the accuracy of the line detection. Additionally, unnecessary line segments are eliminated by the number of pixels and the directional information of the detected line edges. The respects of the experiments emphasize that the proposed algorithm outperforms the existing algorithm which uses small eigenvalue analysis.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.184-191
• /
• 2009

Ideas regarding acting among new theater groups In the 1960s can be summarized in two major trends. The first trend was characterized with the pursuit of identity in a play. The second trend was characterized with the pursuit of creating a play that strongly and passionately explores internal human reality. In their pursuit of the goal of the second trend, they shockingly and strongly destroyed anything by rising in revolt against the existing spatial language. They believed that acting beyond acting as pursued by Stanislavski is not to implant a new type of human, but to develop the self hidden within the actor or to remove the actor's mask. Based on such recognition, the first thing that actors have to do is to remove or break free from the shell or skin that surrounds them. Accordingly, they sought a method that helped them act while taking off their shell or mask during acting and finally got the answer from "improvisation." One thing with improvisation is its way of stimulating the unconscious world of the actors in order to allow them to strongly express the hidden instinctive emotion from deep within them.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.711-720
• /
• 2012

In this paper, we introduce the implementation of driver fatigue monitering system and its result. Input video device is selected commercially available web-cam camera. Haar transform is used to face detection and adopted illumination normalization is used for arbitrary illumination conditions. Facial image through illumination normalization is extracted using Haar face features easily. Eye candidate area through illumination normalization can be reduced by anthropometric measurement and eye detection is performed by PCA and Circle Mask mixture model. This methods achieve robust eye detection on arbitrary illumination changing conditions. Drowsiness state is determined by the level on illumination normalize eye images by a simple calculation. Our system alarms and operates seatbelt on vibration through controller area network(CAN) when the driver's doze level is detected. Our algorithm is implemented with low computation complexity and high recognition rate. We achieve 97% of correct detection rate through in-car environment experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.2
• /
• pp.71-76
• /
• 2016

Digital image processing is being utilized in various fields including medical industry, satellite photos, and factory automation image recognition. However, this kind of image data produces heat by an external cause in the course of being processed, transmitted, and stored. Most typical noises added in the images are AWGN and salt and pepper. MF, CWMF, and AWMF are methods used to restore images damaged by AWGN and the existing methods are likely to damage detailed information such as an edge. Therefore, this paper suggests an algorithm applying weight of average filter, average filter depending on pixel, and spatial weight filter based on edge size of local mask in an AWGN environment, in a different way. Also, this paper compares functions of existing methods by using PSNR to prove excellence of the suggested algorithm.