• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.117-125
• /
• 2011

In this paper, it was segmented the face color distribution using YCbCr color model, which is one of the feature-based methods, and preprocessing stage was to be insensitive to the sensitivity for light which is one of the disadvantages for the feature-based methods by the quantization. In addition, it has raised the accuracy of image synthesis with characteristics which is selected the object of the most same image as the shape of pattern using rough set. In this paper, the detection rates of the proposed face detection algorithm was confirmed to be better about 2~3% than the conventional algorithms regardless of the size and direction on the various faces by simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.4
• /
• pp.645-651
• /
• 2002

This paper presents a method to automatically synthesized human fare images from holistic descriptions. We compactly represent the face set by a small set of prototypes, which can be used in simple ways generated controlled morphings. This becomes possible because separation of 2D-shape and texture provides a faithful, closed and convex representation of images, and smooths the mapping between images and their properties. With this approach, the user watches an images being continuously morphed according to his indications, and the synthesized images always obey the natural physiognomic constraints.

• The Korean Journal of Ceramics
• /
• v.7 no.2
• /
• pp.80-84
• /
• 2001

The anisotropic CdS platelets were synthesized in the lamellar bilayer phase region of the octylamine-water binary system. The influence of the synthesis conditions of the system components on morphology and size of the platelets was examined. Atomic force microscopy (AFM) and high-resolution transmission electron microscopy (HRTEM) studies have shown thickness and face size of the synthesized particles. Platelets with face sizes ranging from 50 to 250 nm and thickness from 10 to 30 nm have been synthesized at room temperature. In addition, HRTEM micrographs show that the synthesized platelets are poly crystal.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.397-400
• /
• 2007

In this paper, we discuss the user-customized interaction for intelligent home environments. The interactive system is based upon the integrated techniques using both speech and face recognition. For essential modules, the speech recognition and synthesis were basically used for a virtual interaction between user and proposed system. In experiments, particularly, the real-time speech recognizer based on the HM-Net(Hidden Markov Network) was incorporated into the integrated system. Besides, the face identification was adopted to customize home environments for a specific user. In evaluation, the results showed that the proposed system was easy to use for intelligent home environments, even though the performance of the speech recognizer did not show a satisfactory results owing to the noisy environments.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.238-241
• /
• 2023

Recently deep learning models are widely used for various tasks such as facial recognition and face editing. Their training process often involves a dataset with imbalanced age distribution. It is because some age groups (teenagers and middle age) are more socially active and tends to have more data compared to the less socially active age groups (children and elderly). This imbalanced age distribution may negatively impact the deep learning training process or the model performance when tested against those age groups with less data. To this end, we propose an age-controllable face synthesis technique using a feature decomposition to classify age from facial images which can be utilized to synthesize novel data to balance out the age distribution. We perform extensive qualitative and quantitative evaluation on our proposed technique using the FFHQ dataset and we show that our method has better performance than existing method.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2022

Although face recognition and face generation have been growing in popularity, the privacy issues of using facial images in the wild have been a concurrent topic. In this paper, we propose a face editing network that can reduce privacy issues by generating face images with various properties from a small number of real face images and facial mask information. Unlike the existing methods of learning face attributes using a lot of real face images, the proposed method generates new facial images using a facial segmentation mask and texture images from five parts as styles. The images are then trained with our network to learn the styles and locations of each reference image. Once the proposed framework is trained, we can generate various face images using only a small number of real face images and segmentation information. In our extensive experiments, we show that the proposed method can not only generate new faces, but also localize facial attribute editing, despite using very few real face images.

• Journal of Broadcast Engineering
• /
• v.20 no.4
• /
• pp.606-618
• /
• 2015

Computer graphics(CG) is being important technique in media contents such as movie and TV. Especially, face replacement technique which replaces the faces between different images have been studied as a typical technology of CG by academia and researchers for a long time. In this paper, we propose the face replacement method between target and reference images under different illumination environment without 3D model. In experiments, we verified that the proposed method could naturally replace the faces between reference and target images under different illumination condition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1136-1141
• /
• 2022

Researches of face recognition on masked faces have been increasingly important due to the COVID-19 pandemic. To realize a stable and practical recognition performance, large amount of facial image data should be acquired for the purpose of training. However, it is difficult for the researchers to obtain masked face images for each human subject. This paper proposes a novel method to synthesize a face image and a virtual mask pattern. In this method, a pair of masked face image and unmasked face image, that are from a single human subject, is fed into a convolutional autoencoder as training data. This allows learning the geometric relationship between face and mask. In the inference step, for a unseen face image, the learned convolutional autoencoder generates a synthetic face image with a mask pattern. The proposed method is able to rapidly generate realistic masked face images. Also, it could be practical when compared to methods which rely on facial feature point detection.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.21-28
• /
• 2011

A 3D face shape derived from 2D images may be useful in many applications, such as face recognition, face synthesis and human computer interaction. To do this, we develop a fast 3D Active Appearance Model (3D-AAM) method using depth estimation. The training images include specific 3D face poses which are extremely different from one another. The landmark's depth information of landmarks is estimated from the training image sequence by using the approximated Jacobian matrix. It is added at the test phase to deal with the 3D pose variations of the input face. Our experimental results show that the proposed method can efficiently fit the face shape, including the variations of facial expressions and 3D pose variations, better than the typical AAM, and can estimate accurate 3D face shape from images.