• 한국멀티미디어학회논문지
• /
• 제22권5호
• /
• pp.535-546
• /
• 2019

Recently, there have been a lot of researches on the whole face replacement system, but it is not easy to obtain stable results due to various attitudes, angles and facial diversity. To produce a natural synthesis result when replacing the face shown in the video image, technologies such as face area detection, feature extraction, face alignment, face area segmentation, 3D attitude adjustment and facial transposition should all operate at a precise level. And each technology must be able to be interdependently combined. The results of our analysis show that the difficulty of implementing the technology and contribution to the system in facial replacement technology has increased in facial feature point extraction and facial alignment technology. On the other hand, the difficulty of the facial transposition technique and the three-dimensional posture adjustment technique were low, but showed the need for development. In this paper, we propose four facial replacement models such as 2-D Faceswap, OpenPose, Deekfake, and Cycle GAN, which are suitable for the Cox platform. These models have the following features; i.e. these models include a suitable model for front face pose image conversion, face pose image with active body movement, and face movement with right and left side by 15 degrees, Generative Adversarial Network.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.1029-1032
• /
• 1999

Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tissue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific face image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from 2D marker movement using neural network. This also 3D motion estimation from 2D point or flow information in captered image under restriction of physics based face model.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.105-108
• /
• 2021

Generative adversarial networks (GANs) have reached a great result at creating the synthesis image, especially in the face generation task. Unlike other deep learning tasks, the input of GANs is usually the random vector sampled by a probability distribution, which leads to unstable training and unpredictable output. One way to solve those problems is to employ the label condition in both the generator and discriminator. CelebA and FFHQ are the two most famous datasets for face image generation. While CelebA contains attribute annotations for more than 200,000 images, FFHQ does not have attribute annotations. Thus, in this work, we introduce a method to learn the attributes from CelebA then predict both soft and hard labels for FFHQ. The evaluated result from our model achieves 0.7611 points of the metric is the area under the receiver operating characteristic curve.

• 한국컴퓨터정보학회논문지
• /
• 제17권8호
• /
• pp.31-40
• /
• 2012

본 논문에서는 3차원의 얼굴모델을 생성하여 사용자의 얼굴을 애니메이션 캐릭터의 얼굴에 자연스럽게 합성하는 새로운 방법을 제안한다. 제안된 방법에서는 먼저 정면과 측면의 직교하는 2장의 2차원 얼굴영상을 입력 받아 얼굴의 주요 특징을 템플릿 스테이크를 이용하여 추출하고, 추출된 특징점에 맞게 일반적인 3차원 얼굴 모델을 변형시킴으로써 사용자의 얼굴 형태에 적합한 얼굴 모델을 생성한다. 그리고 2장의 얼굴 영상으로부터 얻어지는 텍스처 맵을 3차원의 얼굴 모델에 매핑하여 현실감 있는 개인화된 얼굴 모델을 생성한다. 그런 다음, 개인화된 3차원의 얼굴모델을 애니메이션 캐릭터 얼굴의 위치, 크기, 표정, 회전 정보를 반영하여 캐릭터 얼굴에 자연스럽게 합성함으로써 현실감 있는 사용자 맞춤형 애니메이션을 제작한다. 실험에서는 제안된 캐릭터 얼굴 합성 방법의 성능을 검증하기 위해서 수행한 여러 가지 실험결과를 보인다. 본 논문에서 제안된 방법은 애니메이션 영화, 게임, 캐릭터를 이용한 여러 가지 응용 분야에서 유용하게 활용될 것으로 기대된다.

• 전자공학회논문지S
• /
• 제35S권7호
• /
• pp.95-102
• /
• 1998

This paper proposes a synchronization method of synthetic facial iamge sequences and synthetic speech. The LP-PSOLA synthesizes the speech for each demi-syllable. We provide the 3,040 demi-syllables for unlimited synthesis of the Korean speech. For synthesis of the Facial image sequences, the paper defines the total 11 fundermental patterns for the lip shapes of the Korean consonants and vowels. The fundermental lip shapes allow us to pronounce all Korean sentences. Image synthesis method assigns the fundermental lip shapes to the key frames according to the initial, the middle and the final sound of each syllable in korean input text. The method interpolates the naturally changing lip shapes in inbetween frames. The number of the inbetween frames is estimated from the duration time of each syllable of the synthetic speech. The estimation accomplishes synchronization of the facial image sequences and speech. In speech synthesis, disk memory is required to store 3,040 demi-syllable. In synthesis of the facial image sequences, however, the disk memory is required to store only one image, because all frames are synthesized from the neutral face. Above method realizes synchronization of system which can real the Korean sentences with the synthetic speech and the synthetic facial iage sequences.

• 한국통신학회논문지
• /
• 제18권7호
• /
• pp.913-921
• /
• 1993

질감매핑은 대부분의 모델기반 부호화 시스템에서 영상합성 방식으로 사용 되어진다. 이 영상합성 방법은 정면 얼굴영상의 질감정보로만 영상을 합성한다. 따라서, 모델이 회전 되었을 때, 질감매핑은 명암측면에서 어색한 영상을 합성할 수 있다. 본 논문에서는 명암효과를 고려한 새로운 질감매핑이 연구되었다. 또한 회전에 대비하여 귀의 철선프레임과 머리카락의 변화를 부가하였다. 제안된 방식을 이용하여 실험한 결과, 자연스러운 영상합성이 가능하였다.

• Advances in nano research
• /
• 제5권3호
• /
• pp.253-260
• /
• 2017

We report a simple eco-friendly process for the synthesis of gold nanoparticles (AuNPs) using aqueous extract from Coffea Arabica fruit. The formation of AuNPs was confirmed using absorption spectroscopy and scanning electron microscopy images. FT-IR analysis demonstrates the major functional groups present in Coffee Arabica fruit extract before and after synthesizing AuNPs. The Face Center Cubic (FCC) polycrystalline nature of these particles was identified by X-Ray diffraction (XRD) analysis. Taking into account the contribution of the biomass surrounding the AuNPs, dynamic light scattering (DLS) results revealed an average particle size of ~59 nm.

• Journal of Industrial and Engineering Chemistry
• /
• 제68권
• /
• pp.6-13
• /
• 2018

Well-modified amino-appended ${\beta}$-cyclodextrin ($AA-{\beta}-CD$) with an amino group at the primary face of the ${\beta}-CD$ was synthesized and used in the catalytic synthesis of chromeno pyrimido[1,2-b]indazol as supramolecular catalysts in water for the first time. $AA-{\beta}-CD$ was characterized by FT-IR, NMR, MALDI-TOF mass spectrometry, and SEM analysis. A possible reaction mechanism featuring molecular complexation was suggested based on 2D NMR (ROESY) spectroscopy, FE-SEM, DSC, and FT-IR. Advantages such as operational simplicity, recyclability of the catalysts, and accessibility in aqueous medium render this protocol eco-friendly.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.16-25
• /
• 2018

The talking head (TH) indicates an utterance face animation generated based on text and voice input. In this paper, we propose the generation method of TH with facial expression and intonation by speech input only. The problem of generating TH from speech can be regarded as a regression problem from the acoustic feature sequence to the facial code sequence which is a low dimensional vector representation that can efficiently encode and decode a face image. This regression was modeled by bidirectional RNN and trained by using SAVEE database of the front utterance face animation database as training data. The proposed method is able to generate TH with facial expression and intonation TH by using acoustic features such as MFCC, dynamic elements of MFCC, energy, and F0. According to the experiments, the configuration of the BLSTM layer of the first and second layers of bidirectional RNN was able to predict the face code best. For the evaluation, a questionnaire survey was conducted for 62 persons who watched TH animations, generated by the proposed method and the previous method. As a result, 77% of the respondents answered that the proposed method generated TH, which matches well with the speech.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제2권2호
• /
• pp.120-133
• /
• 2008

This paper presents a novel approach for facial motion tracking and facial expression cloning to create a realistic facial animation of a 3D avatar. The exact head pose estimation and facial expression tracking are critical issues that must be solved when developing vision-based computer animation. In this paper, we deal with these two problems. The proposed approach consists of two phases: dynamic head pose estimation and facial expression cloning. The dynamic head pose estimation can robustly estimate a 3D head pose from input video images. Given an initial reference template of a face image and the corresponding 3D head pose, the full head motion is recovered by projecting a cylindrical head model onto the face image. It is possible to recover the head pose regardless of light variations and self-occlusion by updating the template dynamically. In the phase of synthesizing the facial expression, the variations of the major facial feature points of the face images are tracked by using optical flow and the variations are retargeted to the 3D face model. At the same time, we exploit the RBF (Radial Basis Function) to deform the local area of the face model around the major feature points. Consequently, facial expression synthesis is done by directly tracking the variations of the major feature points and indirectly estimating the variations of the regional feature points. From the experiments, we can prove that the proposed vision-based facial expression cloning method automatically estimates the 3D head pose and produces realistic 3D facial expressions in real time.