• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.143-146
• /
• 2007

객체의 특징점을 추출할 때, 일반적으로 모델 기반 접근을 사용한다. 본 논문에서는 이러한 모델 기반 특징점 추출 알고리즘으로 PCA를 근간으로 하는 Active Appearance Model을 이용하는데, 기존의 AAM 알고리즘은 모든 특징점을 하나의 군집으로 기준하여 PCA를 수행하지만 본 논문에서는 이것을 각 주요 부위별 학습 모델로 분리하여 수행한다. 그리고 이러한 모델에서 특징점을 찾을 때, 발산하는 문제에 빠지지 않기 위한 방법을 제시한다. 제시한 방법의 모델을 이용하여 실험 할 경우의 결과와 이를 통한 개별 모델의 특성에 대하여 파악한 결과를 제시한다.

• Journal of Multimedia Information System
• /
• 제5권1호
• /
• pp.15-20
• /
• 2018

There are a lot of problems in the face detection area. One of them is detecting faces by facial features and reducing number of the false negatives and positions. This paper is directed to solve this problem by the proposed triangle method. Also, this paper explans cascades, Haar-like features, AdaBoost, HOG. We propose a scheme using 12-net, 24-net, 48-net to scan images and improve efficiency. Using triangle method for frontal pose, B and B1 methods for other poses in neural networks are proposed.

• 대한인간공학회지
• /
• 제24권4호
• /
• pp.7-13
• /
• 2005

We developed an accurate and reliable photogrammetric method available instead of the direct measurement method and the three-dimensional scanning method. Our research was restricted to a head on the body. Approaching three-dimensionally, we calibrated a distorted image of a photograph and got linear equations of camera beams. Then we assigned z values of landmarks in the head and obtained three-dimensional coordinates for each landmark putting those z values in linear equations of camera beams and finally could calculate measurement results from those three-dimensional coordinates. When we compared results obtained by a program, 'Venus Face Measurement(VFM)' that we had developed applying our method with results obtained by the direct measurement method, VFM showed very accurate and reliable results. In conclusion the photogrammetric method developed in this study was testified to an outstanding measurement method as a substitute for the direct measurement method and the three-dimensional scanning method.

• 한국정보과학회논문지:정보통신
• /
• 제33권6호
• /
• pp.428-437
• /
• 2006

최근 몇년간 무선 애드-흑 라우팅을 위한 많은 스킴들이 광범위하게 연구되었다. 위치기반 라우팅은 애드-혹 라우팅의 한 부류로써, 각 중계노드는 자신 및 목적지, 그리고 이웃노드들의 위치정보에 기반하여 독립적으로 다음-홉(next-hop) 노드를 선택한다. 이러한 위치기반 라우팅은 라우팅 상태 정보를 유지해야 하는 부담이 없기 때문에 대규모 애드-혹 망에 적합하다. 그러나, 위치기반 라우팅은 발신지와 목적지 사이에 빈공간(void)이 존재할 경우 매우 긴 우회 경로를 선택하는 문제를 안고 있다. 이 문제를 해결하기 위해, 본 논문에서는 랜드마크를 이용하는 위치기반 라우팅 방안(GLR)을 제안한다. GLR은 랜드마크(landmark)라고 불리우는 중계노드를 재귀적으로 발견하고 랜드마크 사이를 연결하는 서브패스(sub-path)를 구성한다. 다양한 망 위상에서 행해진 시뮬레이션 결과를 통해서, 제안된 방안(GLR)이 위치기반 라우팅의 성능을 크게 향상시킬 수 있음을 보인다.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제42권
• /
• pp.17.1-17.11
• /
• 2020

Background: To evaluate the facial asymmetry, three-dimensional computed tomography (3D-CT) has been used widely. This study proposed a method to quantify facial asymmetry based on 3D-CT. Methods: The normal standard group consisted of twenty-five male subjects who had a balanced face and normal occlusion. Five anatomical landmarks were selected as reference points and ten anatomical landmarks were selected as measurement points to evaluate facial asymmetry. The formula of facial asymmetry index was designed by using the distances between the landmarks. The index value on a specific landmark indicated zero when the landmarks were located on the three-dimensional symmetric position. As the asymmetry of landmarks increased, the value of facial asymmetry index increased. For ten anatomical landmarks, the mean value of facial asymmetry index on each landmark was obtained in the normal standard group. Facial asymmetry index was applied to the patients who had undergone orthognathic surgery. Preoperative facial asymmetry and postoperative improvement were evaluated. Results: The reference facial asymmetry index on each landmark in the normal standard group was from 1.77 to 3.38. A polygonal chart was drawn to visualize the degree of asymmetry. In three patients who had undergone orthognathic surgery, it was checked that the method of facial asymmetry index showed the preoperative facial asymmetry and the postoperative improvement well. Conclusions: The current new facial asymmetry index could efficiently quantify the degree of facial asymmetry from 3D-CT. This method could be used as an evaluation standard for facial asymmetry analysis.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권1호
• /
• pp.43-50
• /
• 2016

본 논문에서는 ASM(Active Shape Model) 특징점(Landmark)을 이용하여 정밀한 얼굴영역을 획득하고, 외형기반 접근법으로 표정을 인식하는 방법에 대하여 제안한다. 외형기반 표정인식은 EHMM(Embedded Hidden Markov Model) 및 이진패턴 히스토그램 특징과 SVM(Support Vector Machine)을 사용하는 알고리즘으로 구성되며, 제안 방법의 성능평가는 공인 CK 데이터베이스와 JAFFE 데이터베이스를 이용하여 수행되었다. 더불어, 성능비교는 기존의 눈 거리 기반의 얼굴 정규화 방법과 비교를 통하여 수행되었고, 또한 ASM 전체 특징점 및 변형된 특징을 SVM으로 인식하는 기하학적 표정인식 방법론과 성능비교를 수행하였다. 실험 결과, 제안 방법은 거리기반 얼굴정규화 영상을 사용한 방법보다 CK 데이터베이스 및 JAFFE 데이터베이스 경우, 최대 6.39%와 7.98%의 성능향상을 보였다. 또한, 제안 방법은 기하학적 특징점을 사용한 방법보다 높은 인식 성능을 보였으며, 이로부터 제안하는 표정인식 방법의 효용성을 확인하였다.

• 방송공학회논문지
• /
• 제26권5호
• /
• pp.608-620
• /
• 2021

최근 딥러닝 기반의 얼굴 초해상화 연구는 일반적인 영상에 대한 초해상화 연구와 달리 인간의 얼굴이 가지는 구조적 혹은 의미론적인 특성을 반영한 안면 랜드마크 정보, 주요 영역 딕셔너리와 같은 사전 및 참조 정보를 사용하여 우수한 초해상화 결과를 보였다. 그러나 얼굴에 특화된 사전 정보를 사용할 시 추가적인 처리 소요 시간과 메모리를 요구하는 단점이 존재한다. 본 논문은 앞서 언급한 한계점을 극복하고자 지식 증류 기법을 활용한 효율적인 초해상화 모델을 제안한다. 주요 얼굴 영역 기반의 딕셔너리 정보를 사용하는 선생 모델에 지식 증류 기법을 적용하여 추론 시 랜드마크 정보와 부가적인 딕셔너리 사용이 필요 없는 학생 모델을 구축하였다. 제안하는 학생 모델은 특징맵 기반의 적대적 지식 증류를 통해 얼굴 주요 영역 딕셔너리를 가지고 있는 선생 모델로부터 학습을 진행하였다. 본 논문은 제안하는 학생 모델의 실험 결과를 통해 정량 및 정성적으로 우수함을 보이며 선생 모델의 연산량에 비해 90% 이상 절감되는 효율성을 증명한다.

• 대한한의학회지
• /
• 제42권4호
• /
• pp.102-119
• /
• 2021

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, using a fully automated facial shape analysis system, we show that facial morphological features are associated with cold pattern. Methods: The facial morphological features calculated from 68 facial landmarks included the angles, areas, and distances between the landmark points of each part of the face. Cold pattern severity was determined using a questionnaire and the cold pattern scores (CPS) were used for analysis. The association between facial features and CPS was calculated using Pearson's correlation coefficient and partial correlation coefficients. Results: The upper chin width and the lower chin width were negatively associated with CPS. The distance from the center point to the middle jaw and the distance from the center point to the lower jaw were negatively associated with CPS. The angle of the face outline near the ear and the angle of the chin line were positively associated with CPS. The area of the upper part of the face and the area of the face except the sensory organs were negatively associated with CPS. The number of facial morphological features that exhibited a statistically significant correlation with CPS was 37 (unadjusted). Conclusions: In this study of a Korean population, subjects with a high CPS had a more pointed chin, longer face, more angular jaw, higher eyes, and more upward corners of the mouth, and their facial sensory organs were relatively widespread.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.212-218
• /
• 2022

In this paper, the necessity of AI video interview arises when conducting an interview for acquisition of excellent talent in a non-face-to-face situation due to similar situations such as Covid-19. As a matter to be supplemented in general AI interviews, it is difficult to evaluate the reliability and qualitative factors. In addition, the AI interview is conducted not in a two-way Q&A, rather in a one-sided Q&A process. This paper intends to fuse the advantages of existing AI interviews and video interviews. When conducting an interview using AI image analysis technology, it supplements subjective information that evaluates interview management and provides quantitative analysis data and HR expert data. In this paper, image-based multi-modal AI image analysis technology, bioanalysis-based HR analysis technology, and web RTC-based P2P image communication technology are applied. The goal of applying this technology is to propose a method in which biological analysis results (gaze, posture, voice, gesture, landmark) and HR information (opinions or features based on user propensity) can be processed on a single screen to select the right person for the hire.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.