• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.217-220
• /
• 2007

In this paper, we present a new anchor shot detection system which is a core step of the preprocessing process for the news video analysis. The proposed system is composed of four modules and operates sequentially: 1) skin color detection module for reducing the candidate face regions; 2) face detection module for finding the key-frames with a facial data; 3) vector representation module for the key-frame images using a non-negative matrix factorization; 4) anchor shot detection module using a support vector data description. According to our computer experiments, the proposed system shows not only the comparable accuracy to the recent other results, but also more faster detection rate than others.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.55.2-55
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region efface candidate. The feature information in the region of face candidate is used to detect a face region. In the recognition step, as a tested, the 360 images of 30 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression, Input variables of the neural networks are the feature information that comes from the eigenface spaces. The simulation results of 30 persons show that the proposed method yields high recognition rates.

• 한국CDE학회논문집
• /
• 제13권6호
• /
• pp.403-411
• /
• 2008

The alignment of facial images is crucial for 2D face recognition. This is the same to facial meshes for 3D face recognition. Most of the 3D face recognition methods refer to 3D alignment but do not describe their approaches in details. In this paper, we focus on describing an automatic 3D alignment in viewpoint of quantitative analysis. This paper presents a framework of 3D face alignment and normalization based on feature points obtained by Active Shape Models (ASMs). The positions of eyes and mouth can give possibility of aligning the 3D face exactly in three-dimension space. The rotational transform on each axis is defined with respect to the reference position. In aligning process, the rotational transform converts an input 3D faces with large pose variations to the reference frontal view. The part of face is flopped from the aligned face using the sphere region centered at the nose tip of 3D face. The cropped face is shifted and brought into the frame with specified size for normalizing. Subsequently, the interpolation is carried to the face for sampling at equal interval and filling holes. The color interpolation is also carried at the same interval. The outputs are normalized 2D and 3D face which can be used for face recognition. Finally, we carry two sets of experiments to measure aligning errors and evaluate the performance of suggested process.

• 한국컴퓨터정보학회논문지
• /
• 제28권12호
• /
• pp.1-7
• /
• 2023

딥러닝의 발전은 의료 분야에서도 다양한 응용을 가능하게 하고 있으며 이러한 애플리케이션 중에 심박수 측정은 개인의 건강을 관리하기 위한 필수적인 아이템이라 할 수 있다. 광혈류 측정을 이용한 기존 방법의 경우 스마트워치 같은 장비의 착용이 필수적이다. 그러나 최근 딥러닝 기술의 발전은 비침습식으로 원격에서 사용자의 얼굴 이미지를 분석하여 심박수를 높은 성능으로 측정가능하게 한다. 본 연구에서는 모바일 환경에서 사용 가능한 경량화된 심박수 추정 방법론을 제안한다. 이 방법론은 2D 컨볼루션에 기반한 특화된 2채널 네트워크 구조를 사용하여, 혈류와 근육 수축으로 인한 얼굴의 미세한 움직임과 색상 변화를 고려한다. 제안하는 네트워크 구조는 이미지 특성을 분석하는 인코더와 혈류량 파동을 예측하는 회귀 레이어로 구성되어있다. 이러한 복합적인 특성을 동시에 분석함으로써, 제한된 컴퓨팅 리소스를 가진 환경에서도 심박수를 정확하게 추정할 수 있다. 이 연구의 접근 방식은 침습적인 기술 없이도 심박수를 효과적으로 모니터링 할 수 있는 새로운 경로를 제공할 것으로 예상한다.

• 한국산학기술학회논문지
• /
• 제14권7호
• /
• pp.3319-3325
• /
• 2013

본 논문에서는 일상생활에서 생활 의학의 한 방편으로 사용되고 있는 수지침이 실제 인체장기에 어떤 영향을 미치는지에 대해 IT 기술을 적용하여 이를 규명하는 연구를 행하고자 한다. 이를 위해 우선적으로 수지침 요법을 기반으로 인체에 있어 가장 중요한 장기인 심장을 대상으로 심장과 관련된 손 반사점인 A16 혈자리를 5분간 자극하여 전과 후의 얼굴 영상을 수집하고 Lab 색체계를 적용하여 심장과 연관된 이마와 입술 영역에 대한 색상 측정을 통해 상호간의 비교, 분석을 수행하였다. 최종적으로 생체 영상신호의 변화량 측정에 의해 A16 혈자리 자극으로 심장기능에 미치는 효과를 규명하는 연구를 수행하였으며 실험 결과 자료들에 대해 유의성 분석을 통해 실험 결과 자료가 유효한 결과 자료인지 여부에 대한 규명을 행하고자 한다.

• 정보처리학회논문지B
• /
• 제16B권4호
• /
• pp.299-308
• /
• 2009

AAM(Active Appearance Model)은 PCA(Principal Component Analysis)를 기반으로 객체의 형태(shape)와 질감(texture) 정보에 대한 통계적 모델을 통해 얼굴의 특징점을 검출하는 알고리즘으로 얼굴인식, 얼굴 모델링, 표정인식과 같은 응용에 널리 사용되고 있다. 하지만, AAM알고리즘은 초기 값에 민감하고 입력영상이 학습 데이터 영상과의 차이가 클 경우에는 검출 에러가 증가되는 문제가 있다. 특히, 입을 다문 입력얼굴 영상의 경우에는 비교적 높은 검출 정확도를 나타내지만, 사용자의 표정에 따라 입을 벌리거나 입의 모양이 변형된 얼굴 입력 영상의 경우에는 입술에 대한 검출 오류가 매우 증가되는 문제점이 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 입술 특징점 검출을 통해 정확한 입술 영역을 검출한 후에 이 정보를 이용하여 AAM을 수행함으로써 얼굴 특징점 검출 정확성을 향상시키는 방법을 제안한다. 본 논문에서는 AAM으로 검출한 얼굴 특징점 정보를 기반으로 초기 입술 탐색 영역을 설정하고, 탐색 영역 내에서 Canny 경계 검출 및 히스토그램 프로젝션 방법을 이용하여 입술의 양 끝점을 추출한 후, 입술의 양 끝점을 기반으로 재설정된 탐색영역 내에서 입술의 칼라 정보와 에지 정보를 함께 결합함으로써 입술 검출의 정확도 및 처리속도를 향상시켰다. 실험결과, AAM 알고리즘을 단독으로 사용할 때보다, 제안한 방법을 사용하였을 경우 입술 특징점 검출 RMS(Root Mean Square) 에러가 4.21픽셀만큼 감소하였다.

• 혜화의학회지
• /
• 제20권1호
• /
• pp.51-63
• /
• 2011

There are two methods in inspection diagnosis(望診), the viewing shape(觀形) and the inspecting color(察色). Acquiring proper analysis from viewing shape(觀形) requires several standards of shape that can be compared with. We can identify major defects and flaws of the shape from comparing it with the standards that is defined as very normal shape. Also, It can eventually provide us interpretation of health related meanings of the objective shapes. Those standards need symmetrical and proportional details. In this research, I put some physiognomy and inspection diagnosis related documents, and standards for restorative plastic surgery together to suggest standards on viewing shape diagnosis of nose which is one of the most important spot in facial inspection. It is expected to improve delicacy of Oriental medine's inspection diagnosis, as the result of the comparison between plastic surgery and inspection diagnosis.

• 한국의류산업학회지
• /
• 제22권2호
• /
• pp.240-249
• /
• 2020

This study reviews studies that used skin temperature in order to establish an emotion evaluation protocol based on skin temperature for home appliances. A survey of skin temperature evaluation papers was conducted by the following five stages: (1) keyword search, (2) title screening, (3) abstract screening, (4) full paper screening, and (5) relevance evaluation. Selected papers were reviewed for: purpose, recruitment criteria of participants, the number of participants, apparatus, procedure, measures, analysis methods, and major findings. Thermistor sensors and thermography are used for the measurement of skin temperature. Skin temperature sensors are attached to 4 - 10 locations on the body and their mean of skin temperature is calculated by Ramanatan's 4-point or Hardy & Dubois's 7-point method. Semantic differential (SD) method and thermography measuring facial surface temperature have been used for emotion evaluation. The SD method provides a set of adjective pairs related to a product and evaluates changes in emotion from the use of the product. The range of facial surface analyzed is defined in the thermal image and temperature changes before and after the evaluation are analyzed. The evaluation items of home appliances include form, color, material, aesthetics, satisfaction, novelty, convenience, pleasantness, and excellence. Many existing emotion studies using skin temperature do not apply physiological and psychological methods. This study provides basic data to establish a skin temperature and emotion evaluation protocol by examining literature for skin temperature and evaluation of sensitivity.

• 복식문화연구
• /
• 제18권2호
• /
• pp.229-244
• /
• 2010

This study aims to discuss the type and characteristics of primitivism in the modern fashion of the $21^{st}$ century and, as a research method, the concept of primitivism as well as the transition of the patterns of primitivism expressed in modern art have been considered and reviewed through a variety of references. In particular, an empirical analysis of the works that have been created from 2000 to 2009 has been performed using domestic and overseas fashion and collection magazines. The characteristics of primitivism in modern fashion possess the following types of expression: First, Sensuality can be cited as one of the characteristics, either by using direct or indirect exposure of the human body, a silhouette which fits tightly to the body, or creating the effect of sensual beauty using animal fur or bird feathers. Second, Incantation: Masks symbolizing primitive incantation are used to cover the human face or primitive incantation is incorporated as a theme of hair accessories or fashion trinkets, etc. In addition, such decorations as tattoos and the body colorations of ancient tribes are reproduced in modern fashion by means of body painting, printing or other accessories, emphasizing the image of occult primitiveness. Third, Naturalness can be cited as one of the characteristics. Naturalness is emphasized in modern fashion not through artificial decorations and processing, but rather through different patterns of exposure by which natural purity can be felt or through the use of non-artificial materials which recalls primitive civilization. Forth, Playfulness is expressed in the form of graffiti or abstract letters and paintings, and the character of the play is often expressed by the use of grotesque images based on various distortions and exaggerations of the human body, the utilization of symbols of primitive incantation and body and/or facial painting. Fifth, Lastly 'folkishness is emphasized. Folk-like objects, facial decorations, exposure of the body and intense color contrasts typically represent the folkish characteristics.

• 대한치과기공학회지
• /
• 제18권1호
• /
• pp.95-115
• /
• 1996

The esthetic factor for the esthetic prosthesis were studied on 300 persons. The praaticipants were 150 students registered under the Deparment of Dental Laboratoy Technology, Jisan Junior College at the present day of June, 1995 and their mothers. The results were as follows; 1. The number of persons with 28 teeth in their oralcatity was highest(P<0.01). They complained that they have only 28 teeth bacaues of the loss(deficiency) fo teeth due to their impacted teeth and dental caries. 2. The presons with feelings of dissatisfaction were large in number(P<0.01). They were dissatisfied with an abnormal tooth form(33.5%), tooth position(31.7%), tooth color(31.1%), and tooth size(3.7%) in order(P<0.01). 3. In their facial form, the most numerous were men with square form and women with ovoid form(P<0.01). Among the whloe number fo facial forms it appeared to decresae in the order of ovoied(41.8%), square(32.7%), square+tapered(20.5%), and tapered form(5%)(P<0.01). In a profile form, the most numerous were men with A form and women with B. Among the whole participants the most numerous were persons with B form and persons with A and C form were next in oder of numbers(P<0.01). 4. In discoloration of teeth, the most numerous were persons who have no discoloration. 5. In the esthetic recovery of anterior prosthesis the color matching of proximal teeth was not correct, but the outline of proximal teeth was to be reproduced correctly. 6. In the diastema of teeth, the number of persons who have no diastema was higher than that of persons who have a disatema(P<0.01) Among the persons who have diastema the most numerous were persons who have a diastema, and next were 2, 4, 3 and 5 diastemas in order. 7. In a meeting point of the midline of the body and the tooth the number of person hanving a meeting point was higher than that of persons who did not fit each other(P<0.01). The bias direction of midline teeth appeared to be affected by chewing direction, prosthesis location, and posterior location. 8. The length and width of teeth in the tooth size were suitable(P<0.01). The number of persons who have central teeth longer than lateral teeth was high(P<0.0). 9. In the results of smile analysis, the line form connected with incisal edge of upper canine were parallel(P<0.01). When smile the location fo upper lips should be in accord with the central area of teeth(P<0.01) and lower lip should be atteched to the edge of anterior teeth in order to be esthetic. 10. Among the number of upper teeth we can see the most numerous were 8 teeth and next were 10, 6 and 12 in order.