• IEIE Transactions on Smart Processing and Computing
• /
• 제2권1호
• /
• pp.27-35
• /
• 2013

This paper proposes a face tracking algorithm for a viewpoint adaptive multi-view synthesis system. The original scene captured by a depth camera contains a texture image and 8 bit gray-scale depth map. From this original image, multi-view images that correspond to the viewer's position can be synthesized using geometrical transformations, such as rotation and translation. The proposed face tracking technique gives a motion parallax cue by different viewpoints and view angles. In the proposed algorithm, the viewer's dominant face, which is established initially from a camera, can be tracked using the statistical characteristics of face colors and deformable templates. As a result, a motion parallax cue can be provided by detecting the viewer's dominant face area and tracking it, even under a heterogeneous background, and synthesized sequences can be displayed successfully.

• 반도체디스플레이기술학회지
• /
• 제15권2호
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2001년도 추계학술대회 논문집
• /
• pp.309-312
• /
• 2001

FEM simulating system of the cross-rolling texture formation offers a systematic and efficient way of exploring the relationship between the process variables and the state of plastic anisotropy of sheet product. Cross-rolled sheets possess higher average plastic strain ratios and lower planer anisotropy than those of the straight-rolled sheets. The employed model is a finite-element polycrystal model which each element used in FEM is assumed to be a crystal having different orientation by Takahashi. Texture development, deformation textures due to cross-rolling are predicted for face-centered cubic sheet metal. Crystal orientations are assigned on the basis of the pole figures obtained by X-ray diffraction. Development of anisotropy during cross rolling of an fcc sheet material is predicted theoretically with respected to flow stress and R-value in tensile test.

• 대한한방소아과학회지
• /
• 제16권2호
• /
• pp.23-37
• /
• 2002

We have plenty of study of adults diseases, but not much has been said about children. 79 children who had visited in the weak children of Dongeui Oriental Medical Hospital from March, 2002 to October, 2002, were the respondents of the Weak Child Questionnaire. The results obtained were as follows: 1. Their symptoms have been observed with sequences of respiratory diseases, Digestive diseases, Psycho-neurological diseases. 2. Distribution of sex and ages : male 38 cases, female 41 cases. $0{\sim}6$ years 60 cases, $7{\sim}12$ years 17 cases, $13{\sim}18$ years 2 cases. 3. The texture of complexion was resulted in face color and the region of the face : whitish-2/ cases. yellowish-27 cases, darkish-22 cases, blue-2 cases, flushed face-l case. Sangeun(山根)-blue : 59 cases, a lower eyelid- dark or light brown : 54 cases. the rests of color on face region didn't mean. 4. The texture of tongue was ended in tongue state : tongue form-not plump not haggard patten(57 cases), a pricky patten(12), a map patten(7), a fissured patten(3). tongue color- pink (57 cases), red(16), light white(6). coating color- thin white(61 cases), thin yellow(l0), lack(6), deep and white(2). tongue coating substance-thin(72 cases), moisten(5), dry(1), deep(1).

• 환경위생공학
• /
• 제18권2호
• /
• pp.75-86
• /
• 2003

This study was designed to identify the relationship between general characteristics and personalities of college students majoring in beauty art. For this, 286 female students from two colleges in Kwangju were interviewed using a questionnaire pertaining to their general characteristics, hair-style and personality from September 20 through 30, 2001. A $x^2{\;}-{\;}test$ was implemented to identify the relationship between hair-style, personality and other variables. The results are summarized as follows: 1 To define characteristics in relation with hair-style, how students decide their hair-style was examined and, as a result, it was reported that 80.8% of targeted students decided by themselves and 19.2% decided by others' suggestions. 2. It is reported that there was no statistically significant relationship among socio-demographic characteristics such as the length of hair, grades, allowances, religion, satisfaction of campus life, and characteristics relating to hair-style such as accessories, mood, shape of face, decision of hair-style, and texture of hair. 3. Their preference of perm type had a statistically significant relationship with their allowance, religion and accessories, but not with their grades, satisfaction of campus life, mood, shape of face, hair-style, and texture of hair. 4. Dye and bleach had a statistically significant relationship with the texture of hair, but not with socio-demographic characteristics and accessories, mood, shape of face and decision of hair-style. 5. Personality of tenacity, extroversion and introversion, emotion and falsehood had no statistically significant relationship with hair-style. Finally, it was proven that strength, extroversion and introversion, emotion and falsehood had no statistically significant relationship with hair-style. More studies to identify personal tendencies that may affect hair-style are necessary.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권3호
• /
• pp.266-274
• /
• 2007

본 논문에서는 하향식 기계 학습 및 반복적 오차 역투영음 이용하여 한 장의 저해상도 얼굴 영상으로부터 고해상도 얼굴 영상을 복원하는 방법을 제안한다. 먼저 얼굴 영상을 독립된 형태 기저와 질감 기저의 선형 중첩으로 표현하고, 주어진 저해상도 얼굴 영상을 형태 기저와 질감 기저의 선형 중첩으 로 최대한 근사하게 표현할 수 있는 계수를 추정한다. 이 추정된 계수를 고해상도 얼굴 영상의 형태 기저 와 질감 기저의 선형 중첩 계수로 사용함으로써 고해상도 얼굴 영상을 복원한다. 또한, 복원된 고해상도 얼굴 영상의 정확도를 개선하기 위하여 학습 기반 오차 역투영 과정을 반복적으로 적용한다. 다양한 실험을 통하여, 제안된 방법이 저해상도 얼굴 영상으로부터 고해상도 얼굴 영상을 효과적으로 복원함을 입증하였으며, 이 방법을 사용하여 원거리 감시 시스템에서 획득된 저해상도 얼굴 영상을 고해상도 얼굴 영상으로 합성함으로써, 얼굴 인식 시스템의 성능을 높일 수 있음을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• 한국정보통신학회논문지
• /
• 제7권2호
• /
• pp.328-333
• /
• 2003

본 논문에서는 얼굴의 표정 변화에 영향을 주는 해부학에 기반한 18개의 근육군쌍을 바탕으로 하여 얼굴 표정 애니메이션을 위한 근육의 움직임을 조합할 수 있도록 하였다. 개인의 이미지에 맞춰 메쉬를 변형하여 표준 모델을 만든 다음, 사실감을 높이기 위해 개인 얼굴의 정면과 측면 2장의 이미지를 이용하여 메쉬에 매핑하였다. 얼굴의 표정 생성을 애니메이션 할 수 있는 원동력이 되는 근육 모델은 Waters의 근육모델을 수정하여 사용하였다. 이러한 방법을 사용하여 텍스처가 입혀진 변형된 얼굴을 생성하였다. 또한, Ekman이 제안한 6가지 얼굴 표정을 애니메이션 하였다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제17권1호
• /
• pp.9-16
• /
• 2011

본논문에서는 3차원 3D 얼굴 스캔 데이터와 사진 이미지를 이용하여 3D 얼굴 모델을 생성하고 향후의 얼굴을 예측하는 시스템 개발에 대해 기술한다. 본 시스템은 3차원 텍스처매핑, 얼굴 정의 파라미터 입력 도구, 3차원 예측 알고리즘으로 구성 되어 있다. 3차원 텍스처매핑 기능에서는 3D 스캐너로 획득한 얼굴 모델과 사진 이미지를 이용하여 특정 연령에서의 새로운 얼굴모델을 생성한다. 텍스처매핑은 3D 스캐너로부터 획득한 메쉬 데이터에 정면과 좌우 측면의 세 방향의 사진 이미지를 이용하여 매핑하였다. 얼굴 정의 파라미터 입력도구는 3차원 텍스처매핑에 필요한 사용자 인터페이스 도구로서, 얼굴 모델의 정확한 재질값을 얼굴 사진으로부터 얻기 워하여 사진과 3D 얼굴 모델의 특징점을 일치시키는데 사용된다. 본 연구에서는 한 얼굴의 향후 연령대에서의 얼굴 모델을 구하기 위하여 100여개의 얼굴 스캔 데이터베이스를 이용한 통계적 분석에 의해 재질값을 예측 계산하여 해상도 높은 재질값을 가지는 모든 연령대의 3D 얼굴모델을 구성하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권7호
• /
• pp.1705-1720
• /
• 2013

Human face gender recognition requires fast image processing with high accuracy. Existing face gender recognition methods used traditional local features and machine learning methods have shortcomings of low accuracy or slow speed. In this paper, a new framework for face gender recognition to reach fast face gender recognition is proposed, which is based on Local Ternary Pattern (LTP) and Extreme Learning Machine (ELM). LTP is a generalization of Local Binary Pattern (LBP) that is in the presence of monotonic illumination variations on a face image, and has high discriminative power for texture classification. It is also more discriminate and less sensitive to noise in uniform regions. On the other hand, ELM is a new learning algorithm for generalizing single hidden layer feed forward networks without tuning parameters. The main advantages of ELM are the less stringent optimization constraints, faster operations, easy implementation, and usually improved generalization performance. The experimental results on public databases show that, in comparisons with existing algorithms, the proposed method has higher precision and better generalization performance at extremely fast learning speed.