• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.13-19
• /
• 2023

In this paper, we investigated the implementation of a hairstyle recommendation system based on big data and deepfake technology. The proposed hairstyle recommendation system recognizes the facial shapes based on the user's photo (image). Facial shapes are classified into oval, round, and square shapes, and hairstyles that suit each facial shape are synthesized using deepfake technology and provided as videos. Hairstyles are recommended based on big data by applying the latest trends and styles that suit the facial shape. With the image segmentation map and the Motion Supervised Co-Part Segmentation algorithm, it is possible to synthesize elements between images belonging to the same category (such as hair, face, etc.). Next, the synthesized image with the hairstyle and a pre-defined video are applied to the Motion Representations for Articulated Animation algorithm to generate a video animation. The proposed system is expected to be used in various aspects of the beauty industry, including virtual fitting and other related areas. In future research, we plan to study the development of a smart mirror that recommends hairstyles and incorporates features such as Internet of Things (IoT) functionality.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.10
• /
• pp.631-642
• /
• 2003

We propose an approach to extract and to classify facial features into some classes from one's photo as prepared classification standards to generate one's avatar. Facial Feature Extraction and Classification was executed at eyes, nose, lips, jaw separately and I presented each facial features and classification standards. Extracted Facial Features are used for calculation to features of professional designer's facial component images. Then, most similar facial component images are mapped onto avatar's vector face.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.944-947
• /
• 2022

Due to the coronavirus pandemic, the wearing of a mask has been increasing worldwide; thus, the importance of image analysis on masked face images has become essential. Although head pose estimation can be applied to various face-related applications including driver attention, face frontalization, and gaze detection, few studies have been conducted to address the performance degradation caused by masked faces. This study proposes a new data augmentation that synthesizes the masked face, depending on the face image size and poses, which shows robust performance on BIWI benchmark dataset regardless of mask-wearing. Since the proposed scheme is not limited to the specific model, it can be utilized in various head pose estimation models.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.33-38
• /
• 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 race 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 fare model.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.817-828
• /
• 2004

In this paper, we propose vector-based face generation system that uses montage and shading method and preserves designer(artist)'s style. Proposed system generates character's face similar to human face automatically using facial features that extracted from a photograph. In addition, unlike previous face generation system that uses contours, we propose the system is based on color and composes face from facial features and shade extracted from a photograph. Thus, it has advantages that can make more realistic face similar to human face. Since this system is vector-based, the generated character's face has no size limit and constraint. Therefore it is available to transform the shape freely and to apply various facial expressions to 2D face. Moreover, it has distinctiveness with another approaches in point that can keep artist's impression just as it is in result.

• Journal of Korea Game Society
• /
• v.21 no.3
• /
• pp.13-24
• /
• 2021

This paper shows the face rotation applicable to game character facial illustration. Existing studies limited data to human face data, required a large amount of data, and the synthesized results were not good. In this paper, the following method was introduced to solve the existing problems of existing studies. First, a 3D model with features of the input image was rotated and then rendered as a 2D image to construct a data set. Second, by designing GAN that can learn features of various poses from the data built through the 3D model, the input image can be synthesized at a desired pose. This paper presents the results of synthesizing the game character face illustration. From the synthesized result, it can be confirmed that the proposed method works well.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.937-940
• /
• 2020

본 논문은 AI 기술을 기반으로 텍스트 스크립트를 자동으로 인식하고 영상 합성 기술을 응용하여 텍스트 정보를 시각화하는 AI 아나운서 소프트웨어 연구에 대하여 기술한다. 기존의 AI 기반 영상 정보 전달 서비스인 AI 앵커는 텍스트를 인식하여 영상을 합성하는데 오랜 시간이 필요하였으며, 특정 인물 이미지로만 영상 합성이 가능했기 때문에 그 용도가 제한적이었다. 본 연구에서 제안하는 방법은 Tacotron 으로 새로운 음성을 학습 및 합성하여, LRW 데이터셋으로 학습된 모델을 사용하여 자연스러운 영상 합성 체계를 구축한다. 단순한 얼굴 이미지의 합성을 개선하고 다채로운 이미지 제작을 위한 과정을 간략화하여 다양한 비대면 영상 정보 제공 환경을 구성할 수 있을 것으로 기대된다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.25-33
• /
• 2010

In this paper, we propose a simple and efficient algorithm for head pose estimation using a single camera. First, four subimages are obtained from the camera image for face feature extraction. These subimages are used as feature templates. The templates are then tracked by Kalman filtering, and camera projective matrix is computed by the projective mapping between the templates and their coordinate in the 3D coordinate system. And the user's face pose is estimated from the projective mapping between the user's face and image plane. The accuracy and the robustness of our technique is verified on the experimental results of several real video sequences.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.121-123
• /
• 2006

얼굴의 표정은 얼굴의 구성요소 같은 기하학적 정보와 조명이나 주름 같은 세부적인 정보들로 표현된다. 얼굴 표정은 기하학적 변형만으로는 실감적인 표정을 생성하기 힘들기 때문에 기하학적 변형과 더불어 텍스쳐 같은 세부적인 정보도 함께 변형해야만 실감적인 표현을 할 수 있다. 표정비율이미지 (Expression Ratio Image)같은 얼굴 텍스처의 세부적인 정보를 변형하기 위한 기존 방법들은 조명에 따른 피부색의 변화를 정확히 표현할 수 없는 단점이 있다. 따라서 본 논문에서는 이러한 문제를 해결하기 위해 서로 다른 조명 조건에서도 실감적인 표정 텍스처 정보를 적용할 수 있는 비선형 피부색 모델 기반의 표정 합성 방법을 제안한다. 제안된 방법은 동적 외양 모델을 이용한 자동적인 얼굴 특징 추출과 와핑을 통한 표정 변형 단계, 비선형 피부색 변화 모델을 이용한 표정 생성 단계, Euclidean Distance Transform (EDT)에 의해 계산된 혼합 비율을 사용한 원본 얼굴 영상과 생성된 표정의 합성 등 총 3 단계로 구성된다. 실험결과는 제안된 방법이 다양한 조명조건에서도 자연스럽고 실감적인 표정을 표현한다는 것을 보인다.