• 정보처리학회논문지B
• /
• 제10B권4호
• /
• pp.465-472
• /
• 2003

얼굴영상을 효율적으로 처리하기 위해선 먼저 인력영상에서 얼굴영역과 얼굴을 구성하는 각 요소를 검출하고 얼굴의 회전각을 추정하는 전처리과정이 필요하다. 본 논문에서는 다양한 얼굴의 크기와 머리회전, 조명의 변화가 허용되고 피부색과 비슷한 배경이 얼굴에 병합되는 경우에도 얼굴과 요소들(눈, 입)을 강건하게 검출할 수 있는 방법을 제안한다. 변환된 HSV 컬러 좌표계상의 대역적 피부 색상정보와 히스토그램을 이용한 피부 색상정보로 얼굴후보영역을 지정한 뒤, 같은 방법으로 얼굴후보영역 안에서 입술영역을 검출한다. 입술영역의 횡축 기울기로 x축에 대한 회전각을 추정한 후, 얼굴의 모양정보와 요소의 위치정보를 이용해 얼굴임을 확정한다. 다음으로 양안의 조합으로 이루어진 부분 템플릿매칭을 통해 눈을 검출한 뒤, 얼굴의 넓이를 참조한 3차원 공간상에서의 눈의 위치를 계산하여 y축 회전각을 추정한다. 다양한 얼굴영상에 대해 실험을 실시한 결과, 본 알고리즘의 유효성을 확인하였다.

• Geomechanics and Engineering
• /
• 제30권4호
• /
• pp.363-372
• /
• 2022

One of the most frequent issues in tunnel excavation is the collapse of rock blocks and the dropping of rock fragments from the tunnel face. The tunnel face can be reinforced using a number of techniques. One of the most popular and affordable solutions is the use of face longitudinal dowels, which has benefits including high strength, flexibility, and ease of cutting. In order to examine the reinforced face, this work shows the longitudinal deformation profile and ground response curve for a tunnel face. This approach is based on assumptions made during the analysis phase of problem solving. By knowing the tunnel face response and dowel behavior, the interaction of two elements can be solved. The rock element equation derived from the rock bolt method is combined with the dowel differential equation to solve the reinforced ground response curve (GRC). With a straightforward and accurate analytical equation, the new differential equation produces the reinforced displacement of the tunnel face at each stage of excavation. With simple equations and a less involved computational process, this approach offers quick and accurate solutions. The FLAC3D simulation has been compared with the suggested analytical approach. A logical error is apparent from the discrepancies between the two solutions. Each component of the equation's effect has also been described.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권6호
• /
• pp.531-541
• /
• 2022

This study surveyed 233 students who experienced non-face-to-face and face-to-face classes in "86 first-year, 76 second-year, and 71 third-year students" enrolled in the radiology department of universities in the Seoul metropolitan area. The main question of questionnaire consisted of a total of 14 questions, including online lectures and face-to-face lectures, use of electronic devices during classes, students' thoughts on flipped learning methods, and finally, whether it was helpful for students who were unable to participate in face-to-face classes due to COVID-19 to take classes online. The responses were composed optional to select the content of the questionnaire and descriptive to obtain open thinking from students. Comparing the significance level of responses of second and third graders based on the first graders, p>0.05 for second graders and p<0.05 for third graders, showing a significant difference in satisfaction with third graders who were greatly damaged by COVID-19 and freshmen. In conclusion, even in a situation where face-to-face lectures can be conducted, it is considered beneficial for students to conduct online lectures and face-to-face lectures according to the method of the major subject.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.125-133
• /
• 2021

Due to Covid-19, the un-contact culture has affected society as a whole, and the methods of education conducted offline has been greatly affected. In the private education of preparing for university entrance, the public official examinations and certification acquisition, the method of online education has been shown to have positive effects. While private class and school class which have offered in off-line to cope with rapid changes caused various problems such as decline in quality for education. Due to the characteristic of design class, practical training is important. As interactive feedback between students and educators is more important than one-way of delivering knowledge while class is conducted in online, educators have a challenge when they prepare for class. This study handles the methods of online education for the purpose of practical education methods in university nowadays, Especially, the non-face-to-face education methods for game animation production. Based on this study, I propose an effective educational method with non-face-to-face class that allows students to be satisfied and increases their knowledge, beyond face-to-face class.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 SMICS 2004 International Symposium on Maritime and Communication Sciences
• /
• pp.106-109
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of variability in scale, location, orientation and pose. In this paper, we present an efficient linear discriminant for multi-view face detection. Our approaches are based on linear discriminant. We define training data with fisher linear discriminant to efficient learning method. Face detection is considerably difficult because it will be influenced by poses of human face and changes in illumination. This idea can solve the multi-view and scale face detection problem poses. Quickly and efficiently, which fits for detecting face automatically. In this paper, we extract face using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected face and eye detect. The purpose of this paper is to classify face and non-face and efficient fisher linear discriminant..

• 대한전자공학회논문지SP
• /
• 제48권4호
• /
• pp.59-66
• /
• 2011

본 논문은 영상에서 장면 일루미넌트와 카메라의 위치에 따라 다양한 색과 형태로 나타나는 얼굴을 찾기 위해 색 항등성과 기하학적 분석 기반 검출 기법을 제안한다. 색 항등성 기법을 적용하여 영상에서 장면 일루미넌트의 영향을 제거하고, 기하학적 분석을 통해 다양한 형태로 나타나는 얼굴의 검출한다. 제안한 기법은 색 항등성 기법이 적용된 영상에서 얼굴과 헤어 후보영역을 추출하고, 다양한 기준을 이용하여 후보 영역을 분류한다. 그리고 각 얼굴 후보 영역을 대상으로 헤어 후보 영역과의 교차 영역을 계산하여 얼굴로 판단한다. Caltech Face DB내의 영상들을 이용하여 타 기법과의 성능을 비교하였고, 유색 조명 효과가 부가된 영상들을 대상으로 장면 일루미넌트에 대한 성능을 평가하였다. 실험 결과 제안한 기법은 다양한 입력 영상에서 얼굴 검출이 가능하였고 TP와 낮은 FN 수치로 나타났다.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.412-420
• /
• 2020

This paper proposes a performance-improving face recognition system based on a super resolution method for low-resolution images. The conventional face recognition algorithm has a rapidly decreased accuracy rate due to small image resolution by a distance. To solve the previously mentioned problem, this paper generates a super resolution images based o deep learning method. The proposed method improved feature information from low-resolution images using a super resolution method and also applied face recognition using a feature extraction and an classifier. In experiments, the proposed method improves the face recognition rate when compared to conventional methods.

• 한국임상보건과학회지
• /
• 제10권1호
• /
• pp.1543-1552
• /
• 2022

Purpose: It is intended to investigate the satisfaction of dental hygiene students with non-face-to-face online classes and use them as basic data for successful lecture design and operation. Methods: The data collected in this study were analyzed using the lBM SPSS Statistics 21 program. The general characteristics of the study subjects were frequency analysis, non-face-to-face online class satisfaction, and test satisfaction were frequency analysis and technical statistics. Through the independent sample T test, a t-test was conducted to find out whether there was an average difference in online class and test satisfaction according to grade. Results: The advantages of non-face-to-face online classes were that repetitive learning was possible (57.7%), the disadvantage was that there was a lack of real-time communication (74.9%), and the most efficient teaching method was a mixed form of online and face-to-face classes (64.9%). The satisfaction level of online classes was 2.69 points for 'self-directed learning habits,' which was the highest compared to the overall average of 2.55 points, and 2.09 points for 'difficulty in interaction between instructors and learners in online classes.'Non-face-to-face test satisfaction was 2.68 points for 'short test time gives fairness to test results,' higher than the overall average of 2.45 points, and 2.07 points for 'no difficulty accessing the test.'In terms of satisfaction with the non-face-to-face test according to the grade, it was found that the third grade showed a more negative attitude than the second grade in terms of sexual fairness (p<0.05). Conclusions: Through the above results, non-face-to-face online classes require various content development and some mixed classes considering the level of students, and instructors' efforts to improve the quality of classes for interaction between instructors and learners are needed.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권11호
• /
• pp.809-817
• /
• 2002

본 논문은 온라인 얼굴 인식에서 전처리에 해당하는 얼굴 검출방법을 다룬다. 기존의 얼굴 검출 방법에서 에지 정보만을 이용한 얼굴 검출 방법과 컬러 정보를 이용한 얼굴 검출 방법의 단점을 상호 보완하기 위해 본 연구에서는 에지 정보와 컬러 정보를 결합한 얼굴 검출 방법 및 중심 영역 컬러 샘플링을 이용한 얼굴 검출방법을 개발하였다. 즉, 사람의 얼굴 영역이 비슷한 컬러를 가진 배경 영역과 결합(Merge)되는 것을 막기 위해 먼저 적응형 에지 검출 알고리즘을 수행하여 배경과 얼굴 영역을 각각의 고립 영역으로 분할한다. 제안된 적응형 소벨(Sobel) 에지 검출기는 배경 영역과 얼굴 영역의 경계에서 항상 에지가 발생할 수 있도록 에지가 많이 검출되고 입력 영상의 밝기 변화에 강인하다. 이로 인해 얼굴 영역이 하나의 영역이 아닌 여러 영역으로 분할되어 나타날 수 있으므로, 각 영역들의 컬러 정보를 이용해 병합한 후, 최종 얼굴 영역을 MBR(minimum bounding rectangle) 형태로 검출하였다. 이때 병합된 최종 얼굴 영역 후보가 너무 크거나 혹은 너무 작으면, 중심 영역 샘플링 방법을 이용해 다시 얼굴 영역을 검출한다. 총 2100장의 얼굴 영상 데이터베이스를 통해 실험한 결과 본 연구에서 제안한 방법을 사용해 96.3%의 높은 얼굴 영역 검출 성공률을 얻을 수 있었다.