• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• 대한의용생체공학회:의공학회지
• /
• 제37권5호
• /
• pp.195-207
• /
• 2016

This study examined the effectiveness of micro-current stimulation (MCS) to improve the facial skin qualities by performing clinical test. The MCS is generally known that provide healing response in the damaged tissue and pain relief through activating the adenosine triphosphate (ATP) and protein synthesis. In here, we can hypothesize that the improvement of facial skin qualities may occur due to MCS, since the induction of micro-current from outside may enhance the cellular activity according to ATP activation. From the clinical test, our results showed that a variety of evaluating categories, which is able to assess the skin qualities, significantly enhanced due to stimulation of micro-current after 7 and 14 days. Therefore, we can estimate that MCS in human facial skin may be effective to improve the skin qualities.

• 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.

• 대한화장품학회지
• /
• 제28권3호
• /
• pp.91-108
• /
• 2002

미백제는 기미와 태양광선노출에 의한 색소침착반과 같은 색소불균형이 주로 나타나는 동양 여성들에 특히 관심이 많다. 이러한 색소침착의 불균형은 UV에 의해 더 심해지기 때문에 미백제는 멜라닌합성을 억제시키거나 UV에 의해 활성화된 signal을 억제함으로써 효과가 나타난다. Eumelanin은 UV에 의해 유도된 DNA 손상을 보호하므로 UV에 의해 유도된 DNA손상을 감소시키는 물질이 이상적인 미백제가 된다. 새롭게 합성된 항산화제인 $\alpha$-tocophenyl ferulate의 효과는 UV에 의해 손상된 DNA damage에 의한 보호 효과와 멜라닌 합성을 억제시킴으로서 나타난다. Chemical peeling과 복합적으로 색소 반점을 치료하는 lightning agent의 효과에 대한 결과를 보고하였으며 색소 반점의 개선을 정량적으로 평가하는 새롭게 개발된 facial image analyzer를 소개할 것이다.

• 인터넷정보학회논문지
• /
• 제23권2호
• /
• pp.71-77
• /
• 2022

본 연구에서는 음성 합성 모델을 감정에 따라 음성을 합성하는 모델로 확장하고 감정에 따른 얼굴 표정을 생성하기 위한 데이터 베이스를 수집한다. 데이터베이스는 남성과 여성의 데이터가 구분되며 감정이 담긴 발화와 얼굴 표정으로 구성되어 있다. 성별이 다른 2명의 전문 연기자가 한국어로 문장을 발음한다. 각 문장은 anger, happiness, neutrality, sadness의 4가지 감정으로 구분된다. 각 연기자들은 한 가지의 감정 당 약 3300개의 문장을 연기한다. 이를 촬영하여 수집한 전체 26468개의 문장은 중복되지 않으며 해당하는 감정과 유사한 내용을 담고 있다. 양질의 데이터베이스를 구축하는 것이 향후 연구의 성능에 중요한 역할을 하므로 데이터베이스를 감정의 범주, 강도, 진정성의 3가지 항목에 대해 평가한다. 데이터의 종류에 따른 정확도를 알아보기 위해 구축된 데이터베이스를 음성-영상 데이터, 음성 데이터, 영상 데이터로 나누어 평가를 진행하고 비교한다.

• 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.

• Bulletin of the Korean Chemical Society
• /
• 제35권6호
• /
• pp.1743-1748
• /
• 2014

A facile and effective method has been developed for the synthesis of a novel series of benzofuran derivatives via N-acylation, O-alkylation and intramolecular condensation reactions, starting from readily available substituted o-hydroxy aryl ketone, and chloroacetyl arylamides. This metal-free transition process is characterized by mild reaction conditions, atom economy, short reaction time and a high yield with a decreased amount of by-products.

• 대한화장품학회지
• /
• 제23권3호
• /
• pp.9-23
• /
• 1997

Retinoids are essential regulators of spithelial cell growth and celluar differentiation. They are also known to be effective in photoaging. It was reported that topical application of retinoic acid improves facial wrinkle carsed by collagen synthesis reduction in photodamaged skin. Collagen synthesis by retinoic acid may contribute to the wrinkle effacement. Since celluar retinoic acid binding protein II is slsctively induced in human skin and dermal fibroblasts in vitro by retinoic acid, this response can be used to mesure retinoids potency and activity. In order to know the activity of retinoids and their relations with collagen synthesis, we treated dermal fibroblasts with retinoids for 48 hours at 10-6-10-7M and measured CRABPII mRNA level by quantitative Nortern blotting. We also measured the rate of collagen systhesis by retinoids using 3-dimensional dermal equivalent. CRABPII mRNA level was increased 3-fold by retinoic acid, 2.1-fold by retinol and 1.4-fold by retinaldehyde. Collagen systhesis was increased 34% by all-trans retinioc acid, 26% by retinol, 17% by retinaldehyde and 7% by retinyl palmitate. From the above results, retinoids were found to be a potent indecers of CRABPII mRNA and collagen synthesis. Though retinoic acid was the most effective, its use has been restricted because of the side effects. Instead, retinol can be a best candidate in cosmetics for the treatment of photodamaged skin in terms of efficacy and safety.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 1998년도 추계학술발표 논문집
• /
• pp.40-44
• /
• 1998

사용자에 게 친근감 있는 인터페이스를 제공하기 위해 자연스러운 얼굴 애니메이션에 대한 연구가 활발히 진행 중이다.[5][6] 본 논문에서는 자연스러운 얼굴의 표정 합성을 위한 애니메이션 방법 을 제안하였다. 특정한 사람을 모델로 한 얼굴 애니메이션을 위하여 우선 3차원 메쉬로 구성된 일반 모델(generic model)을 특정 사람에게 정합 하여 특정인의 3차원 얼굴 모델을 얻을 수 있다 본 논문에서는 한국인의 자연스러운 얼굴 표정합성을 위하여, 한국인의 표준얼굴에 관한 연구결과를 토대로 한국인 얼굴의 특징을 반영한 일반모델을 만들고 이를 이용하여 특정인의 3차원 얼굴 모델을 얻을 수 있도록 하였다. 실제 얼굴의 근육 및 피부 조직 등 해부학적 구조에 기반 한 표정 합성방법을 사용하여 현실감 있고 자연스러운 얼굴 애니메이션이 이루어질 수 있도록 하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.111-118
• /
• 1999

Recently computer can make cyberspace to walk through by an interactive virtual reality technique. An a avatar in cyberspace can bring us a virtual face-to-face communication environment. In this paper, an avatar is realized which has a real face in cyberspace and a multiuser communication system is constructed by voice transmitted through network. Voice from microphone is transmitted and analyzed, then mouth shape and facial expression of avatar are synchronously estimated and synthesized on real time. And also an entertainment application of a real-time voice driven synthetic face is introduced and this is an example of interactive movie. Finally, face motion capture system using physics based face model is introduced.