• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.739-741
• /
• 2004

얼굴인식 기술 분야에 있어서 Haar-like feature를 이용한 얼굴 검출 알고리즘은 많은 관련 알고리즘 중에 매우 빠른 트레이닝 시간과 처리속도 향상의 장점을 가지고 있다 그러므로 특히 동영상에서의 얼굴 검출에서 유용하게 쓰일 수 있다. 이러한 방법으로 검출된 얼괄 데이터는 HMM(Hidden Markov Model)알고리즘을 이용하여 이미 트레이닝된 얼굴 데이터베이스와의 비교를 통해 얼굴인식에 있어서 가장 확률이 높은 사람을 본인의 얼굴로 인증하는 신원 확인 시스템을 구현할 수 있게 된다. 신원 확인 시스템에 있어서 얼굴 검출 율이나 신원 확인 성공률은 모두 학습 과정에 의해 결정되기 때문에 얼마나 많은 학습을 효율적으로 하느냐에 따라 성능이 좌우된다. 이러한 시스템은 카메라에 얼굴을 보여주는 것만으로 신원 확인이 가능하기 때문에 번거로운 신원 확인 과정을 거쳐야 하는 다른 시스템 구조에 비해 매우 편리한 기능을 제공할 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.628-631
• /
• 2003

In this paper, we present real-time, accurate face region detection and tracking technique for an intelligent surveillance system. It is very important to obtain the high-resolution images, which enables accurate identification of an object-of-interest. Conventional surveillance or security systems, however, usually provide poor image quality because they use one or more fixed cameras and keep recording scenes without any cine. We implemented a real-time surveillance system that tracks a moving person using four pan-tilt-zoom (PTZ) cameras. While tracking, the region-of-interest (ROI) can be obtained by using a low-pass filter and background subtraction. Color information in the ROI is updated to extract features for optimal tracking and zooming. The experiment with real human faces showed highly acceptable results in the sense of both accuracy and computational efficiency.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.517-519
• /
• 2001

본 논문에서는 신원 확인 시스템을 위한 얼굴 영역 탐지 및 얼굴 구성 요소들을 추출하는 방법을 제안한다. 이 방법은 신원 확인을 위해 사용자가 시스템을 조작할 때, 움직임이 발생한다는 점과 눈 영역이 주위 영역에 비하여 뚜렷하게 어두운 화소들로 구성되어 있다는 점에 착안하였다. CCD 카메라로부터 입력되는 동영상에서 차영상 기법을 이용하여 얼굴 영역을 탐지하고, 탐지된 얼굴 영역 내에서 가장 안정적인 검출 결과를 보이는 눈 영역을 추출한다. 그리고 추출된 두 눈의 위치를 이용하여 전체 얼굴의 기울기를 보정한 수, 제안하는 가변 Ratio Template을 이용하여 검출된 얼굴영역을 검증하며 코, 입과 같은 다른 얼굴 구성 요소들을 추출한다. 이 방법은 명암의 변화에 따라 유동적인 결과를 산출해내는 이진화 과정을 거치지 않으므로 국부적인 조명이 밝기 변화나 얼굴의 기울기 변화와 같은 얼굴 인식의 제약점에 강인한 특징을 가진다.

• Structural Monitoring and Maintenance
• /
• v.2 no.4
• /
• pp.339-355
• /
• 2015

Corrosion of prestressed concrete structures is one of the main challenges that engineers face today. In response to this national need, this paper presents the results of a long-term project that aims at developing a structural health monitoring (SHM) technology for the nondestructive evaluation of prestressed structures. In this paper, the use of permanently installed low profile piezoelectric transducers (PZT) is proposed in order to record the acoustic emissions (AE) along the length of the strand. The results of an accelerated corrosion test are presented and k-means clustering is applied via principal component analysis (PCA) of AE features to provide an accurate diagnosis of the strand health. The proposed approach shows good correlation between acoustic emissions features and strand failure. Moreover, a clustering technique for the identification of false alarms is proposed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.317-318
• /
• 2020

본 논문에서는 얼굴검출 후 MobilnetV2의 방법을 이용하여 적은 연산량으로 CCTV가 실시간으로 마스크 착용 유무를 판단할 수 있는 방법을 제시하였다. 이를 통해 현재 이슈가 되고있는 코로나19 등 전염병의 전염 위험이 있는 주요 장소에서 인공지능 CCTV가 마스크 미착용자를 식별해 알려줌으로써 마스크 미착용자를 관리할 수 있는 방법을 제공하였다.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• Journal of The Korean Association of Information Education
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2008

This study uses the identification which is one of the critical components of psychological mechanism and enables replacing one's own self because of the needs of self-expression(disclosure) and creation. The study aims to improve educational effects using the realistic by increasing sense of the virtual reality and the attention. After the computer-based contents were developed and converted to be applied into robot, and then the contents were combined the student's photo and the avatar using automatic loading. Finally each one of the contents was applied to the students. The results of the investigation indicated that there were significant effects of the contents based on identification. In other words, the contents effect on student's attention, but not their academic achievement. The study could find the effect of the identification's application using the educational robot. We suggested that improving technical ability of the augmented virtuality as a face-detection and sensitive interaction may lead to the specific suggestions for educational effects for further research.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.183-190
• /
• 2011

In this paper, we propose a prototype system for abnormal sound detection and identification which detects and recognizes the abnormal situations by means of analyzing audio information coming in real time from CCTV cameras under surveillance environment. The proposed system is composed of two layers: The first layer is an one-class support vector machine, i.e., support vector data description (SVDD) that performs rapid detection of abnormal situations and alerts to the manager. The second layer classifies the detected abnormal sound into predefined class such as 'gun', 'scream', 'siren', 'crash', 'bomb' via a sparse representation classifier (SRC) to cope with emergency situations. The proposed system is designed in a hierarchical manner via a mixture of SVDD and SRC, which has desired characteristics as follows: 1) By fast detecting abnormal sound using SVDD trained with only normal sound, it does not perform the unnecessary classification for normal sound. 2) It ensures a reliable system performance via a SRC that has been successfully applied in the field of face recognition. 3) With the intrinsic incremental learning capability of SRC, it can actively adapt itself to the change of a sound database. The experimental results with the qualitative analysis illustrate the efficiency of the proposed method.

• 한국노년학
• /
• v.29 no.2
• /
• pp.529-546
• /
• 2009

Depression in old age not only is prevalent but also causes a considerable amount of burden in physical, psychosocial, and economic terms. Intervention, however, is often delayed due to the understanding that considers depressive symptoms as a normal process of aging or signs of physical illnesses. Since the recognition of symptoms often initiate one's help seeking process, a correct identification of symptoms can contribute to early detection and intervention to depression in oneself as well as in others. This study interviewed 104 older adults living in an urban area, and explored their ability to correctly identify depressive symptoms and factors related to identification. The study results show that respondents who were able to correctly identify symptoms of depression were only 14%, and the rest defined the symptoms as social, economic, and other psychological issues. Of the factors in the logistic regression model, age being 75 and over and mass media as source of mental health information affected negatively their ability to correctly identify symptoms; mental health education programs affected positively their ability. Based on these results, it is suggested that such strategies as employing a face-to-face provision of concrete information and counseling can be more effective than delivering information via large-scale lectures. Additionally, a future research deems necessary to conduct an in-depth examination of mental health/illness-related contents on mass media.

• Archives of Plastic Surgery
• /
• v.35 no.4
• /
• pp.423-430
• /
• 2008

Purpose: Computed tomography theoretically should improve detection of foreign bodies and provide more information of adjacent soft tissues. And the CT scanner and PACS program proved to be an excellent instrument for detection and localization of most facial foreign bodies above certain minimum levels of detectability. The severity of injury in penetrating trauma to the face, it is often underestimated by physical examination. Diagnosis of a retained foreign object is always critical. Methods: From March, 2005 to February 2008 a study was done with 200 patients who had facial trauma. Axial and coronal CT images were obtained with a General Electric(Milwaukee, Wis) 9800 CT scanner at 130 kV, 90 mA, with a 2-mm section thickness and a $512{\times}512$ matrix. Results: Axial and coronal CT images at various window widths should be used as the first imaging modality to detect facial foreign bodies. The attenuation coefficients for the metallic and nonmetallic foreign bodies ranged from -437 to +3071 HU. As a general rule, metallic foreign bodies produced more Hounsfield artifacts than nonmetallic foreign bodies, thus providing a clue to their composition. All of the metallic foreign bodies were represented by a single peak and had a maximum attenuation coefficient of +3071 HU. Of the nonmetallic foreign bodies, glass had an attenuation coefficient that ranged from +105 to +2039, while plastic had a much lower coefficient that ranged from -62 to -35. wood had the lowest range of attenuation coefficients: -491 to -437. Conclusion: The PACS program allows one to distinguish metallic from nonmetallic foreign bodies and to individually identify the specific composition of many nonmetallic foreign bodies. This program does not, however, allow identification of the specific composition of a metallic foreign body. We recommend this type of software program for CT scanning of any patient with an injury to the face in which a foreign body is suspected.