• 인터넷정보학회논문지
• /
• 제10권4호
• /
• pp.55-70
• /
• 2009

비전기반 인간컴퓨터 상호작용은 컴퓨터와 인간의 상호소통을 자연스럽게 제공하는 측면에서 과학과 산업분야에서 주목받는 연구 분야이다. 그러한 측면에서 얼굴표정인식에 의한 인간의 심리적 상태를 추론하는 기술은 중요한 이슈이다. 본 연구에서는 감성인식 HMM 모델과 광류에 기반한 얼굴 움직임 추적 방법을 이용하여 동영상으로부터 얼굴표정을 인식하는 새로운 방법을 제시하였다. 특히, 기존의 감성상태 변환을 설명하는 HMM 모델은 특정 표정상태 간의 전환 시 항상 중립 상태를 거치도록 설계되어 있다. 그러나 본 연구에서는 기존의 표정상태 전환 모델에 중간상태를 거치는 과정 없이 특정 표정 상태간의 변환이 가능한 확장된 HMM 모델을 제시한다. 동영상으로부터 얼굴의 특성정보를 추출하기 위하여 탬플릿 매칭과 광류방법을 적용하였다. 광류에 의해 추적된 얼굴의 표정특성 정보는 얼굴표정인식을 위한 HMM의 매개변수 정보로 사용된다. 실험을 통하여 제안된 얼굴표정인식 방법이 실시간 얼굴 표정인식에 효과적임을 입증하였다.

• 융합보안논문지
• /
• 제19권1호
• /
• pp.67-78
• /
• 2019

본 논문에서는 가변 크기 블록 기반의 새로운 얼굴 특징 표현 방법을 제안한다. 기존 외형 기반의 얼굴 표정 인식 방법들은 얼굴 특징을 표현하기 위해 얼굴 영상 전체를 균일한 블록으로 분할하는 uniform grid 방법을 사용하는데, 이는 다음 두가지 문제를 가지고 있다. 얼굴 이외의 배경이 포함될 수 있어 표정을 구분하는 데 방해 요소로 작용하고, 각 블록에 포함된 얼굴의 특징은 입력영상 내 얼굴의 위치, 크기 및 방위에 따라 달라질 수 있다. 본 논문에서는 이러한 문제를 해결하기 위해 유의미한 표정변화가 가장 잘 나타내는 블록의 크기와 위치를 결정하는 가변 크기 블록 방법을 제안한다. 이를 위해 얼굴의 특정점을 추출하여 표정인식에 기여도가 높은 얼굴부위에 대하여 블록 설정을 위한 기준점을 결정하고 AdaBoost 방법을 이용하여 각 얼굴부위에 대한 최적의 블록 크기를 결정하는 방법을 제시한다. 제안된 방법의 성능평가를 위해 LDTP를 이용하여 표정특징벡터를 생성하고 SVM 기반의 표정 인식 시스템을 구성하였다. 실험 결과 제안된 방법이 기존의 uniform grid 기반 방법보다 우수함을 확인하였다. 특히, 제안된 방법이 형태와 방위 등의 변화가 상대적으로 큰 MMI 데이터베이스에서 기존의 방법보다 상대적으로 우수한 성능을 보여줌으로써 입력 환경의 변화에 보다 효과적으로 적응할 수 있음을 확인하였다.

• Journal of Acupuncture Research
• /
• 제33권4호
• /
• pp.101-108
• /
• 2016

Objectives : Among the assessment tools for evaluating facial function, the House-Brackmann scale is used as a standard tool, but it has some shortcomings. The Sunnybrook Facial Grading System can assess the after effects of facial palsy and facial movement by each part of the face. By understanding the application state of this Sunnybrook Facial Grading System, we intend to analyze the relationship between House-Brackmann scale score and Sunnybrook Facial Grading System score so that we can examine the advantages of the Sunnybrook Facial Grading System as a more accurate tool. Methods : We screened both inpatients and outpatients who visited the Facial Palsy Center at Kyung Hee University Hospital for Korean medical treatment and were evaluated with the Sunnybrook Facial Grading System from December 2015 to October 2016. A total of 159 out of 166 patients were studied, including basic characteristics and missing data. We used descriptive statistics for general features of patients and SPSS Ver.18 for statistical analysis. Results : House-Brackmann scale and Sunnybrook Facial Grading System have high negative correlation through Pearson Correlation Coefficient with a score of -0.884. Analyzing outlier data resulting from relation analysis between the House-Brackmann scale and the Sunnybrook Facial Grading System showed many outliers when the damaged state of each part of the face is different. Conclusion : Sunnybrook Facial Grading System can make up for faults of the House-Brackmann scale, which is inferior in accuracy when each damage status of each part of the face is different. Sunnybrook Facial Grading System performs a detailed assessment of facial function and sequelae of facial palsy easier than the House-Brackmann scale.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.175-178
• /
• 2001

This paper proposes a novel human-computer interaction system for the disabled using recognition of face direction. Face direction is recognized by comparing positions of center of gravity between face region and facial features such as eyes and eyebrows. The face region is first selected by using color information, and then the facial features are extracted by applying a separation filter to the face region. The process speed for recognition of face direction is 6.57frame/sec with a success rate of 92.9% without any special hardware for image processing. We implement human-computer interaction system using screen menu, and show a validity of the proposed method from experimental results.

• 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.

• International Journal of Contents
• /
• 제8권1호
• /
• pp.16-22
• /
• 2012

In this paper we propose a method for verifying video in a video telephony system implemented in DM6446 DaVinci Processor. Each frame is categorized either error free frame or error frame depending on the predefined criteria. Human face is chosen as a basic means for authenticating the video frame. Skin color based algorithm is implemented for detecting the face in the video frame. The video frame is classified as error free frame if there is single face object with clear view of facial features (eyes, nose, mouth etc.) and the background of the image frame is not different then the predefined background, otherwise it will be classified as error frame. We also implemented the image histogram based NCC (Normalized Cross Correlation) comparison for video verification to speed up the system. The experimental result shows that the system is able to classify frames with 90.83% of accuracy.

• 한국정보기술학회 영문논문지
• /
• 제8권2호
• /
• pp.47-58
• /
• 2018

In this paper, we propose a method for skin condition analysis using a camera module embedded in a smartphone without a separate skin diagnosis device. The type of skin disease detected in facial image taken by smartphone is acne, pigmentation, blemish and flush. Face features and regions were detected using Haar features, and skin regions were detected using YCbCr and HSV color models. Acne and flush were extracted by setting the range of a component image hue, and pigmentation was calculated by calculating the factor between the minimum and maximum value of the corresponding skin pixel in the component image R. Blemish was detected on the basis of adaptive thresholds in gray scale level images. As a result of the experiment, the proposed skin condition analysis showed that skin diseases of acne, pigmentation, blemish and flush were effectively detected.

• Journal of Genetic Medicine
• /
• 제18권1호
• /
• pp.70-74
• /
• 2021

Cohen-Gibson syndrome (CGS) was first reported by Cohen et al., who identified the mutation of the gene encoding the embryonic ectoderm development (EED) in a patient with phenotypes similar to Weaver syndrome. CGS manifests as an overgrowth and intellectual disability, in addition to the characteristic facial features and organ anomalies. CGS has been reported in only 11 unrelated patients since 2015. A girl aged 6 years and 3 months presented with seizures. She had macrosomia, a dysmorphic face, and intellectual disability. Her mother and younger sister and brother also had macrosomia, intellectual disability, and similar facial features; additionally, her mother experienced seizures and had an arachnoid cyst, while her siblings had valvar pulmonary stenosis. Whole-exome sequencing for the proband revealed a mutation of EED (c.581A>G, p.Asn194Ser), which was also verified in the mother and both siblings using Sanger sequencing. This is the first report of familial CGS.

• 인터넷정보학회논문지
• /
• 제3권6호
• /
• pp.13-24
• /
• 2002

본 논문에서는 색상 정보와 변형 모델을 이용한 얼굴 영역 및 얼굴의 특징 영역의 자동 검출 방법을 제시한다. 영상으로부터 획득할 수 있는 정보 중 가장 빠르고 쉽게 얻을 수 있는 정보가 색상 정보이며, 색상정보는 사물을 판단함에 있어서 가장 효율적이면서 컴퓨터의 계산량을 줄일 수 있다는 장점을 갖고 있기 때문에 얼굴 영역 검출 방법으로 많이 이용되고 있다. 본 연구에서는 얼굴영역 및 얼굴 특성 추출함에 있어 컬러모델 사용 시 외부 조명의 영향을 줄여주는 조명 보정 방법을 제시하고, 조명 보정에 의해 평활화 된 YCbCr 색상모델에 적용하여 각 성분 특성을 고려한 얼굴영역 및 얼굴의 특성 영역에 해당하는 후보 영역을 검출하는 방법을 제시한다. 검출된 얼굴후보 영역 및 특성 영역은 가변 모델인 동적 윤곽선 모델의 초기 값으로 자동 적용되어 윤곽선 모델 적용 시 문제점가운데 하나인 초기 값 설정문제를 해결함과 동시에 얼굴 및 얼굴 특징 정보의 정확한 윤곽선을 추출하는데 사용된다. 실험 결과 제시된 방법을 적용한 결과 빠르고 효과적으로 얼굴 및 특성 영역을 검출 할 수 있음을 입증 할 수 있었다. 이상에서 추출된 얼굴의 특성정보는 차후 얼굴 인식 및 얼굴 특성을 설명하는 얼굴 특성 서술자로 사용될 수 있다.

• Archives of Plastic Surgery
• /
• 제39권6호
• /
• pp.606-611
• /
• 2012

Background Facial fractures are infrequent in children and adolescents and have different clinical features from those in adults. The low incidence in children and adolescents reflects the flexibility and underdevelopment of their facial skeletons, as well as their more protected environments. Only a few reports have reviewed such patients in Korea. The authors performed a retrospective study to analyze the characteristics of facial fractures in the Korean pediatric population. Methods We conducted a retrospective review on a series of 741 patients, aged <18 years, with facial fractures who had been treated at our hospital between 2006 and 2010. The following parameters were evaluated: age, sex, cause, location and type of fractures, associated injuries, treatment and complications. Results A total of 741 consecutive patients met the inclusion criteria. The ratio of boys to girls was 5.7:1. Facial fractures most commonly occurred in patients between 13 and 15 years of age (36.3%). The most common causes of injury was violence. The nasal fracture was the most common type of fracture (69%) and the blowout fracture was the second most common (20%). Associated injuries occurred in 156 patients (21%). Conclusions The incidence of pediatric facial fractures caused by violence is high in Korea. Our results show that as age increases, etiological factors and fracture patterns gradually shift towards those found in adults. This study provides an overview of facial fractures in these age groups that helps illustrate the trends and characteristics of the fractures and may be helpful in further evaluation and management.