• 정보보호학회논문지
• /
• 제23권4호
• /
• pp.737-742
• /
• 2013

최근 감시시스템은 휴먼인식 기술을 활용하여 스스로 판단하고 대처할 수 있는 지능형으로 발전하고 있다. 기존 얼굴인식 기술은 근거리에서 인식성능이 우수하지만 원거리로 갈수록 인식률이 떨어진다. 본 논문에서는 원거리 휴먼인식을 위해 거리별 얼굴영상을 학습으로 사용한 얼굴인식에서 보간법 및 얼굴인식 알고리즘에 따른 얼굴인식률의 성능을 분석한다. 영상 정규화에는 최근접 이웃, 양선형, 양3차회선, Lanczos3 보간법을 사용하고, 얼굴인식 알고리즘은 PCA와 LDA를 사용한다. 실험결과, 영상 정규화로 양선형 보간법과 얼굴인식 알고리즘으로 LDA를 사용했을 때 우수한 성능을 나타냄을 확인하였다.

• 한국항행학회논문지
• /
• 제13권5호
• /
• pp.773-780
• /
• 2009

본 논문은 픽셀의 색상과 채도를 퍼지추론한 얼굴영역 검출 알고리즘을 제안하였다. 제안한 알고리즘은 조명보정과 얼굴 검출 과정으로 구성되었다. 조명보정 과정에서는 조명변화에 대한 보정기능을 수행한다. 얼굴 검출 과정은 20개의 피부 색상 모델에서 계산된 색상과 채도를 특징 파라미터로 멤버쉽 함수를 생성하여 유사도를 평가하였다. 추출된 얼굴 후보영역을 CMY칼라 모델에서 C요소로 눈을 검출하였고, YIQ 칼라 공간에서 Q요소로 입을 검출하였다. 추출된 얼굴 후보영역에서 일반적인 얼굴에 대한 지식을 기반으로 얼굴 영역을 검출하였다. 입력받은 정면 칼라 영상으로 실험한 결과, 얼굴 영상의 위치와 크기에 관계없이 얼굴 영역이 검출됨을 알 수 있었다.

• The International Journal of Costume Culture
• /
• 제6권2호
• /
• pp.93-104
• /
• 2003

The purpose of this study was to investigate the relationship between women's face satisfaction and makeup satisfaction, to disclose the differences of makeup satisfaction according to demographic variables, and to examine how makeup satisfaction was influenced by face satisfaction and demographic variables. The subjects were 200 women over age 17 living in Seoul and its peripheral areas. The results of this study were as follows: Face satisfaction were drawn three factors. Factor 1 was face contour satisfaction, Factor 2 was skin satisfaction, and Factor 3 was lips and eyes satisfaction. There were significant positive relationship between factors of face satisfaction and makeup satisfaction. Also, the face contour satisfaction was in positive correlation with satisfaction of features, and the skin satisfaction was in positive correlation with that of features. There were significant positive correlations between makeup satisfaction and face shape, eyes, nose, lips, chin, and cheek bone satisfaction. Face satisfaction didn't show significant difference according to demographic variables, but makeup satisfaction showed significant difference according to age and occupation. Face satisfaction was influenced by the facial face, clarity of skin, elasticity of skin, skin color, and ages. The explanatory power of the 4 variables were 24.5%. Makeup satisfaction was influenced by lips and eyes satisfaction, ages, and skin care level. The explanatory power of the 3 variables were 13.3%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• 대한치과기공학회지
• /
• 제42권3호
• /
• pp.248-253
• /
• 2020

Purpose: This study aimed to verify whether blended learning is worth alternating with traditional face-to-face learning for some dental technology students in practice teaching. Methods: A total of 68 students were included in this study. They were divided into two groups to compare blended learning and traditional face-to-face learning. The experiment had been carried out over 15 weeks. The following tests were performed: test of instructional quality, test of learning satisfaction, test of perceived usefulness, and test of learning flow. The IBM SPSS software was used to analyze the data. Results: The learning satisfaction and the perceived useful of blended learning by students appeared to be higher than that of traditional face-to-face learning. However, there was no significant difference in the variables of traditional face-to-face learning and those of blended learning (p<0.05). Conclusion: Blended learning is an alternative to traditional face-to-face learning for some dental technology students in practice teaching.

• 한국통신학회논문지
• /
• 제30권6C호
• /
• pp.570-576
• /
• 2005

얼굴 인식 분야에서 포즈의 변화는 인식률을 저하시키는 가장 심각한 문제로 알려져 있다. 본 논문에서는 이러한 포즈가 변화된 얼굴 영상에 대한 인식률을 높이기 위한 전처리 단계로 정면이 아닌 얼굴 영상을 정면 얼굴 영상으로 변환시키는 방법을 제안한다. 제안한 방법은 PCA 계수를 선형 변환 시키는 변환 행렬을 사용되는데 이 변환 행렬은 PCA 계수 사이의 선형적인 관계를 이용하여 구한다. 제안된 방법은 PCA/LDA를 이용한 얼굴 인식 알고리즘으로 검증하였으며, 실험 결과 제안된 방법이 얼굴 인식률을 $20\%$ 정도 향상시킴을 알 수 있었다.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• 한국멀티미디어학회논문지
• /
• 제22권5호
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권4호
• /
• pp.45-56
• /
• 2020

Purpose The purpose of this study is to present the direction of efficient e-learning education through the importance and satisfaction survey of learners of non-face-to-face video lectures. Therefore, by grasping the degree of satisfaction of the importance ratio through the IPA analysis method, we try to present improvement measures for insufficient education methods. Design/methodology/approach For IPA analysis, we conducted an online survey of four universities and analyzed 154 samples. The analysis method used SPSS, and through the wordcloud analysis method of R, the suggestions for the non-face-to-face lecture method felt by learners were analyzed to derive implications for improving the quality of education. Findings As a result of the overall satisfaction survey for the entire non-face-to-face class, the factors with the greatest dissatisfaction are listed as follows. Complaints about the adequacy of learning materials and activities (quiz, discussion, assignments, etc.), Complaints about how to use the produced content, and complaints about announcements about class management (lecture schedule, lecture method) were identified in order. The factors of dissatisfaction were clear in the non-face-to-face class where interactive communication was impossible or insufficient. In addition to the lack of quick Q&A, there seems to have been a phenomenon of some neglect.