• 전자공학회논문지
• /
• 제51권11호
• /
• pp.137-145
• /
• 2014

본 논문에서는 지능형 영상 감시시스템을 위한 LDA기반 원거리 얼굴인식 알고리즘을 제안한다. 기존 단일 거리 얼굴영상을 학습으로 사용한 얼굴인식 알고리즘은 원거리로 갈수록 얼굴인식률이 떨어지는 문제점이 있다. 실제 거리별 얼굴영상을 사용한 방법은 얼굴인식률은 향상되지만 사용자가 직접 움직이며 학습용 거리별 얼굴영상을 취득해야하는 문제점이 있다. 그러므로 본 논문에서는 단일 거리에서 취득한 얼굴영상을 이용해 거리별 얼굴영상을 자동으로 생성하여 학습으로 사용하는 방법을 제안한다. 제안하는 방법은 기존 얼굴인식 방법과 동일한 수준의 사용자 협조에서 거리별 사용자 등록영상을 생성할 수 있는 장점이 있다. 실험결과, 제안한 알고리즘은 기존 단일 거리 학습영상 기반 알고리즘에 비해 근거리에서 평균 16.3%, 원거리에서 평균 18.0% 향상된 얼굴인식 성능을 나타냈고, 실제 거리별 얼굴영상을 사용한 방법보다 근거리에서 평균 4.3%감소했지만, 원거리에서는 동일한 얼굴인식 성능을 나타냈다.

• 한국인공지능학회지
• /
• 제5권2호
• /
• pp.15-25
• /
• 2017

Recently, technologies are being developed to recognize and authenticate users using bioinformatics to solve information security issues. Biometric information includes face, fingerprint, iris, voice, and vein. Among them, face recognition technology occupies a large part. Face recognition technology is applied in various fields. For example, it can be used for identity verification, such as a personal identification card, passport, credit card, security system, and personnel data. In addition, it can be used for security, including crime suspect search, unsafe zone monitoring, vehicle tracking crime.In this thesis, we conducted a study to recognize faces by detecting the areas of the face through a computer webcam. The purpose of this study was to contribute to the improvement in the accuracy of Recognition of Face Based on CNN Algorithms. For this purpose, We used data files provided by github to build a face recognition model. We also created data using CNN algorithms, which are widely used for image recognition. Various photos were learned by CNN algorithm. The study found that the accuracy of face recognition based on CNN algorithms was 77%. Based on the results of the study, We carried out recognition of the face according to the distance. Research findings may be useful if face recognition is required in a variety of situations. Research based on this study is also expected to improve the accuracy of face recognition.

• 정보보호학회논문지
• /
• 제33권2호
• /
• pp.353-362
• /
• 2023

전기통신금융사기 범죄인 메신저 피싱은 스마트폰 원격제어와 비대면 금융거래를 악용한 것으로 재산 피해는 물론이고 피해자들의 신용과 채무문제가 발생해 이차 피해가 심각하다. 이러한 금융사고는 피해자들의 부주의도 있겠지만 현재 메신저 피싱 범죄 수법은 지능적이며, 비대면 사용자 확인 절차의 허점을 파고든 결과로도 볼 수 있다. 본 연구에서는 메신저 피싱이 비대면 금융거래 시 사용자 확인 절차의 허점을 어떻게 악용하고 있는지 사례를 중심으로 분석하고, 실험을 통해 더 안전한 금융거래를 위한 비대면 확인 항목별로 개선점을 제언한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.228-246
• /
• 2011

A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy.

• 한국의류학회지
• /
• 제31권11호
• /
• pp.1487-1499
• /
• 2007

In this study, photographs of 600 Korean females aged from 20 to 50years old were indirectly measured in Venus face 2D program. The measurements were analyzed by statistical methods. The purpose of this study was to differentiate the facial types of adult women for the beauty industry. As a result of factor analysis, 6 factors were selected the key factors of facial shape: head height(factor 1), head width(factor 2), side face width(factor 3), head width and circumference(factor 4), face length(factor 5), and side face width(factor 6). We categorized facial type into 5 groups with the previous 6 factor. 5 types were most common facial shapes: Oblong face(type 1), Square face(type 2), Oval face(type 3), Round face(type 4), Triangle face(type 5). The results of facial type analysis were showed that Round face(26.6%), Triangle face(25.3%), Oval face(22.3%), Square face(20.0%), Oblong face(5.7%).

• ETRI Journal
• /
• 제33권2호
• /
• pp.251-258
• /
• 2011

Applying face alignment after face detection exerts a heavy influence on face recognition. Many researchers have recently investigated face alignment using databases collected from images taken at close distances and with low magnification. However, in the cases of home-service robots, captured images generally are of low resolution and low quality. Therefore, previous face alignment research, such as eye detection, is not appropriate for robot environments. The main purpose of this paper is to provide a new and effective approach in the alignment of small and blurred faces. We propose a face alignment method using the confidence value of Real-AdaBoost with a modified census transform feature. We also evaluate the face recognition system to compare the proposed face alignment module with those of other systems. Experimental results show that the proposed method has a high recognition rate, higher than face alignment methods using a manually-marked eye position.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.707-720
• /
• 2014

This paper proposes a face tracking scheme that is a combination of a face detection algorithm and a face tracking algorithm. The proposed face detection algorithm basically uses the Adaboost algorithm, but the amount of search area is dramatically reduced, by using skin color and motion information in the depth map. Also, we propose a face tracking algorithm that uses a template matching method with depth information only. It also includes an early termination scheme, by a spiral search for template matching, which reduces the operation time with small loss in accuracy. It also incorporates an additional simple refinement process to make the loss in accuracy smaller. When the face tracking scheme fails to track the face, it automatically goes back to the face detection scheme, to find a new face to track. The two schemes are experimented with some home-made test sequences, and some in public. The experimental results are compared to show that they outperform the existing methods in accuracy and speed. Also we show some trade-offs between the tracking accuracy and the execution time for broader application.

• 대한방사선기술학회지:방사선기술과학
• /
• 제44권6호
• /
• pp.679-688
• /
• 2021

This study is a questionnaire about the lesson environment that radiation major students prefer in a non-face-to-face live online lesson environment for a total of 133 students, 65 second graders and 68 third graders who are enrolled in the department of radiology at a university located in the Seoul metropolitan area. And checked the satisfactory level by grade. The questionnaire consists of three categories: 1st real-time non-face-to-face lectures, 2nd professor lectures, and 3rd corona lectures. A total of 14 questions, with multiple choice and descriptive response methods. As an evaluation method, in the case of a multiple-choice question, the average was calculated using a 5-point Likert scale. As a result of conducting the independent sample T-test of the SPSS program, the response by grade was P > 0.05, and no significant result was shown by the contents of the questionnaire survey of the second grade. As for the lecture method of the department of radiology after the end of Covid-19 virus, it is better to promote face-to-face lessons in radiation training subjects and non-face-to-face real-time education in subjects centered on radiation theory.

• 한국학교ㆍ지역보건교육학회지
• /
• 제20권3호
• /
• pp.123-134
• /
• 2019

Objectives: The purpose of this study is to identify the problems of verbal violence that adolescents face in the post-human age, when the non-face-to-face media is increasing. Methods: A survey was conducted on 305 adolescents, aged 14 to 16 years of middle school and high school students. The data were analyzed with the SPSS 25.0. Results: As a result of conducting multiple regression analysis to identify the type of conversation that affects verbal abuse of adolescents, a model with a conversation with family, conversation with other people, messenger conversation such as KakaoTalk, and video chat conversation was selected. The amount of explanation was 11.4%. (R2 = .114) Of these, non-face-to-face conversations have been shown to increase verbal violence, and face-to-face conversations with family have, in turn, lowered the risk. As a result of t-testing to examine the effect of verbal abuse experience on the verbal violence index, the damage experience was significant in depression (p = .042) and impulsive aggression (p = .021). (P = .000). Conclusion: This study reiterates the importance of family dialogue along with the fact that the development of various non-face-to-face media in the Fourth Industrial Revolution can have a negative impact on adolescent mental health.

• 한국재난정보학회 논문집
• /
• 제17권4호
• /
• pp.722-732
• /
• 2021

연구목적: 코로나바이러스 감염증-19(COVID) 펜데믹으로 인해 모든 교육기관은 전면 비대면 실시간 교육을 해야하는 상황이 발생하였고 이에 소방공무원에게도 비대면교육을 적용하여 소방교육을 운영하는 것이 요구되었다. 이러한 펜데믹 상황에서 중앙소방학교가 소방공무원에게 실시한 비대면 실시간 교육에 대한 실태조사를 통해 비대면 실시간 교육의 방향을 찾고 개선방안을 제시 하려한다. 연구방법: 소방공무원을 대상으로 '비대면 실시간 원격교육의 질적 향상 및 전문화를 위한 의식조사' 라는 주제로 설문조사를 실시하여 그 결과를 토대로 심층분석을 하였다. 연구결과 및 결론: 첫째, 교수자 혹은 교육운영자는 다양한 프로그램을 활용하여 교육특성에 맞는 원격교육 프로그램을 적극 활용할 필요가 있다. 둘째, 비대면 교육을 위한 전용노트북을 제공하여 모든 학습자들이 교육 참여에 어려움 없는 교육환경을 제공 할 필요가 있다. 셋째, 소방공무원 교육훈련 특성상 장비 활용이 필요한 교육훈련의 경우에는 각 소방서에 교육 장비를 배치하여 비대면 실습교육 장소로 고려해 볼 필요가 있다. 넷째, 실습교육은 이론교육으로 대처하는 것은 만족스러운 교육효과를 기대하기 어렵다. 그렇기에 비대면 실시간 실습교육이 가능한 시설과 프로그램이 개발되어져야한다. 그러한 비대면 실습교육이 가능해지기 전까지는 사회적 거리를 최대한 유지하면서 대면교육을 적절하게 병행하는 것도 고려해볼만 하다. 다섯째, 비대면 교육은컴퓨터 화면의 불빛과 전자파로 인하여 눈의 피로도가 높고 시간이 흐를수록 집중도가 많이 떨어진다는 의견으로 보아 적절한 수업시간과 휴식시간을 통해 학습자의 눈의 피로를 줄이고 집중력을 높일 수 있는 교육시간을 구성해야 할 필요가 있다. 마지막으로 교수자는 일방적인 지식전달을 하는 교육보다는 교수자와 학습자가 상호작용할 수 있는 학습자 참여 중심의 교육을 운영해야할 필요가 있다. 또한 비대면 원격교육 기술적인 문제는 사전시스템 점검을 통해 교육에 차질이 없도록 철저한 준비가 필요한 것으로 생각된다.