• Title/Summary/Keyword: 얼굴감지

Search Result 68, Processing Time 0.034 seconds

The Framework for Cost Reduction of User Authentication Using Implicit Risk Model (내재적 리스크 감지 모델을 사용한 사용자 인증 편의성 향상 프레임워크)

  • Kim, Pyung;Seo, Kyongjin;Cho, Jin-Man;Kim, Soo-Hyung;Lee, Younho
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.27 no.5
    • /
    • pp.1033-1047
    • /
    • 2017
  • Traditional explicit authentication, which requires awareness of the user's authentication process, is a burden on the user, which is one of main reasons why users tend not to employ authentication. In this paper, we try to reduce such cost by employing implicit authentication methods, such as biometrics and location based authentication methods. We define the 4-level security assurance model, where each level is mapped to an explicit authentication method. We implement our model as an Android application, where the implicit authentication methods are touch-stroke dynamics-based, face recognition based, and the location based authentication. From user experiment, we could show that the authentication cost is reduced by 14.9% compared to password authentication-only case and by 21.7% compared to the case where 6-digit PIN authentication is solely used.

2-Stage Detection and Classification Network for Kiosk User Analysis (디스플레이형 자판기 사용자 분석을 위한 이중 단계 검출 및 분류 망)

  • Seo, Ji-Won;Kim, Mi-Kyung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.5
    • /
    • pp.668-674
    • /
    • 2022
  • Machine learning techniques using visual data have high usability in fields of industry and service such as scene recognition, fault detection, security and user analysis. Among these, user analysis through the videos from CCTV is one of the practical way of using vision data. Also, many studies about lightweight artificial neural network have been published to increase high usability for mobile and embedded environment so far. In this study, we propose the network combining the object detection and classification for mobile graphic processing unit. This network detects pedestrian and face, classifies age and gender from detected face. Proposed network is constructed based on MobileNet, YOLOv2 and skip connection. Both detection and classification models are trained individually and combined as 2-stage structure. Also, attention mechanism is used to improve detection and classification ability. Nvidia Jetson Nano is used to run and evaluate the proposed system.

Performance Comparison for Exercise Motion classification using Deep Learing-based OpenPose (OpenPose기반 딥러닝을 이용한 운동동작분류 성능 비교)

  • Nam Rye Son;Min A Jung
    • Smart Media Journal
    • /
    • v.12 no.7
    • /
    • pp.59-67
    • /
    • 2023
  • Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

Style-Generative Adversarial Networks for Data Augmentation of Human Images at Homecare Environments (조호환경 내 사람 이미지 데이터 증강을 위한 Style-Generative Adversarial Networks 기법)

  • Park, Changjoon;Kim, Beomjun;Kim, Inki;Gwak, Jeonghwan
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2022.11a
    • /
    • pp.565-567
    • /
    • 2022
  • 질병을 앓고 있는 환자는 상태에 따라 병실, 주거지, 요양원 등 조호환경 내 생활 시 의료 인력의 지속적인 추적 및 관찰을 통해 신체에 이상이 생긴 경우 이를 감지하고, 신속하게 조치할 수 있도록 해야 한다. 의료 인력이 직접 환자를 확인하는 방법은 의료 인력의 반복적인 노동이 요구되며 실시간으로 환자를 확인해야 한다는 특성상 의료 인력이 상주해야 하기에 이는 곧, 의료 인력의 부족과 낭비로 이어진다. 해당 문제 해결을 위해 의료 인력을 대신하여 조호환경 내 환자의 상태를 실시간으로 모니터링할 수 있는 딥러닝 모델들이 연구되고 있다. 딥러닝 모델은 데이터의 수가 많을수록 강인한 모델을 설계할 수 있으며, 데이터셋의 배경, 객체의 특징 분포 등 다양한 조건에 영향을 받기 때문에 학습에 필요한 도메인을 가지는 많은 양의 전처리된 데이터를 수집해야 한다. 따라서, 조호환경 내 환자에 대한 데이터셋이 필요하지만, 공개된 데이터셋의 경우 양이 매우 적으며 이를 반전, 회전기법 등을이용할 경우 데이터의 수를 늘릴 수 있지만, 같은 분포의 특징을 가지는 데이터가 생성되기에 데이터 증강 기법을 단순하게 적용하면 딥러닝 모델의 과적합을 야기한다. 또한, 조호환경 내 이미지 데이터셋은 얼굴 노출과 같은 개인정보가 포함 될 수 있으며 이를 보호하기 위해 정보들을 비식별화 해야 한다는 문제점이 있다. 따라서 본 논문에서는 조호환경에서 수집된 데이터 증강을 위한 Style-Generative Adversarial Networks 기법을 적용하여 조호환경 데이터셋 수집에 효과적인 증강 기법을 제안한다.

Trend and future prospect on the development of technology for electronic security system (기계경비시스템의 기술 변화추세와 개발전망)

  • Chung, Tae-Hwang;So, Sung-Young
    • Korean Security Journal
    • /
    • no.19
    • /
    • pp.225-244
    • /
    • 2009
  • Electronic security system is composed mainly of electronic-information-communication device, so system technology, configuration and management of the electronic security system could be affected by the change of information-communication environment. This study is to propose the future prospect on the development of technique for electronic security system through the analysis of the trend and the actual condition on the development of technique. This study is based on literature study and interview with user and provider of electronic security system, also survey was carried out by system provider and members of security integration company to come up with more practical result. Hybrid DVR technology that has multi-function such as motion detection, target tracking and image identification is expected to be developed. And 'Embedded IP camera' technology that internet server and image identification software are built in. Those technologies could change the configuration and management of CCTV system. Fingerprint identification technology and face identification technology are continually developed to get more reliability, but continual development of surveillance and three-dimension identification technology for more efficient face identification system is needed. As radio identification and tracking function of RFID is appreciated as very useful for access control system, hardware and software of RFID technology is expected to be developed, but government's support for market revitalization is necessary. Behavior pattern identification sensor technology is expected to be developed and could replace passive infrared sensor that cause system error, giving security guard firm confidence for response. The principle of behavior pattern identification is similar to image identification, so those two technology could be integrated with tracking technology and radio identification technology of RFID for total monitoring system. For more efficient electronic security system, middle-ware's role is very important to integrate the technology of electronic security system, this could make possible of installing the integrated security system.

  • PDF

A Preferred Skin Color by Korean Female in the Age between 30s~40s (30 ~ 40대 한국여성이 선호하는 피부색에 대한 연구)

  • Kang, Nae Gyu;Kwak, Taek Jong;Kim, Jung A;Kim, Tae Hoon;Moon, Tae Kee;Park, Sun Gyoo;Song, Da Young;Lee, Su Jin;Chang, Min Youl;Jang, Hee Jung;Choo, Jung Ha;Jeong, Su Na
    • Journal of the Society of Cosmetic Scientists of Korea
    • /
    • v.40 no.4
    • /
    • pp.373-382
    • /
    • 2014
  • The skin is an organ that covers the outside of the human body. And it regulates body temperature, performs sensory function, deliveries the drug, and represents the abnormality of the internal organs. For these reasons, people have been expressing the condition of the body based on the state of the skin of the face to detect sign of health, "you look well", "face with vitality". Depending on the degree of aging and the environment, it is a fact that skin color, skin texture, moisture and firmness could be different. In particular, the color of the skin acts as a factor that affects to determine the subjective impression such as beauty and charm. We could expect consumer's demand through the market of whitening cosmetics and skin treatment. However, existing most of the cosmetics focus on improving whiteness. The number of studies that focused on skin color is not enough. In this study, we found out the skin color condition by carrying out surveys of 100 women between 30s and 40s. Our study would be very useful to develop new cosmetic products and to satisfy customer's needs.

The study on Byunsangwha(Buddha's preaching paint) of 4 volumes of the script of 80 Avatamska Sutra present in Japan (일본(日本)에 현존(現存)하는 4권의 주본화엄경(周本華嚴經)의 변상획(變相畵)에 관한 연구)

  • Kwon, Hi-Kyung
    • Journal of Korean Society of Archives and Records Management
    • /
    • v.4 no.1
    • /
    • pp.67-85
    • /
    • 2004
  • Four volumes of the script of the Avatamska Sutra written with golden paste on dark blue papers manufactured in Koryo Dynasty which are collected or deposited in every museum of Japan show specific features on their cover paintings. In general 3 or 4 lotus flowers are wound by arabesque patterns in zigzag on the cover paintings of Koryo scripts, whereas 10 lotus flowers painted with golden paste on the 4 volumes of these scripts are same in their style. Though there is no prayer sentences in 4 volumes of the script, it is possible to know that they should belong to a set of 80 Avatamska Sutra by the results of above studies. In this study the contents of Byunsangwha of the script of 4 volumes of the Avatamska Sutra were discussed at first and their manufactured era should be postulated by the results of style analysis of cover paintings and Byunsangwha. First thing that saint hair of Buddha was painted with cobalt color is same as that of Byunsangwha of Munsuchoisangsungmusenggebueob prayed in Tejeong 3rd year, king Chungsuk 13th year(AD 1326). Second thing that the beads in topknot of saint hair and lips were painted completely with pink color, and ears, face outline as well as bosom outline disclosed through monk's cloth were also painted with pink color, furthermore the last thing is that Buddha's face was coated with golden paste. All of these things are same as shown in the characteristics of Byunsangwha of the scripts of Kanezawa Daishoji, Matsue Tenrinji and Haga Tera collection in Japan. However, since the cloud pattern style of Byunsangwha of the script is similar to that of the Byunsangwha manufactured in reinstatement era of king Chungsuk, it is possible to say that these 4 volumes of script should be manufactured in the reinstatement era of king Chungsuk.

Design of an Visitor Identification system for the Front Door of an Apartment using Deep learning (딥러닝 기반 이용한 공동주택현관문의 출입자 식별 시스템 설계)

  • Lee, Min-Hye;Mun, Hyung-Jin
    • Journal of the Korea Convergence Society
    • /
    • v.13 no.4
    • /
    • pp.45-51
    • /
    • 2022
  • Fear of contact exists due to the prevention of the spread of infectious diseases such as COVID-19. When using the common entrance door of an apartment, access is possible only if the resident enters a password or obtains the resident's permission. There is the inconvenience of having to manually enter the number and password for the common entrance door to enter. Also, contactless entry is required due to COVID-19. Due to the development of ICT, users can be easily identified through the development of face recognition and voice recognition technology. The proposed method detects a visitor's face through a CCTV or camera attached to the common entrance door, recognizes the face, and identifies it as a registered resident. Then, based on the registered information of the resident, it is possible to operate without contact by interworking with the elevator on the server. In particular, if face recognition fails with a hat or mask, the visitor is identified by voice or additional authentication of the visitor is performed based on the voice message. It is possible to block the spread of contagiousness without leaving any contactless function and fingerprint information when entering and exiting the front door of an apartment house, and without the inconvenience of access.