• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.451-456
• /
• 1989

New image coding system for facial images called 'Knowledge-based image coding' is described, in which input image is analyzed and output image is synthesized using analysis results. Analysis and synthesis method of facial expressions are presented. Synthesis rules are determined on the basis of facial muscles and are also used in analysis process to produce a faithful reconstruction of the original image. A number of examples are shown.

• Korean Journal of Cognitive Science
• /
• v.11 no.2
• /
• pp.1-10
• /
• 2000

Realistic facial animation research field which communicates with human and computer using face has increased recently. The human face is the part of the body we use to recognize individuals and the important communication channel that understand the inner states like emotion. To provide the intelligent interface. computer facial animation looks like human in talking and expressing himself. Facial modeling and animation research is focused on realistic facial animation recently. In this article, we suggest the method of facial modeling and animation for realistic facial synthesis. We can make a 3D facial model for arbitrary face by using generic facial model. For more correct and real face, we make the Korean Generic Facial Model. We can also manipulate facial synthesis based on the physical characteristics of real facial muscle and skin. Many application will be developed such as teleconferencing, education, movies etc.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• 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.

• Journal of the HCI Society of Korea
• /
• v.6 no.1
• /
• pp.21-26
• /
• 2011

This paper presents a robust method for facial image synthesis under varying illumination by combining illumination correction and Poisson image processing techniques. The presented method automatically detects skin area and corrects highly saturated regions that can cause bad effects on the final synthesis image. The developed method can be applied to various facial synthesis applications by correcting illumination variations that can occur frequently on photos taken with a camera phone.

• Journal of KIISE:Software and Applications
• /
• v.27 no.6
• /
• pp.618-631
• /
• 2000

In this paper, we suggest the method of 3D facial synthesis using the motion of 2D facial images. We use the optical flow-based method for estimation of motion. We extract parameterized motion vectors using optical flow between two adjacent image sequences in order to estimate the facial features and the facial motion in 2D image sequences. Then, we combine parameters of the parameterized motion vectors and estimate facial motion information. We use the parameterized vector model according to the facial features. Our motion vector models are eye area, lip-eyebrow area, and face area. Combining 2D facial motion information with 3D facial model action unit, we synthesize the 3D facial model.

• Journal of KIISE:Software and Applications
• /
• v.27 no.8
• /
• pp.827-833
• /
• 2000

Facial expression is an effective tool to express human emotion. In this paper, a facial expression analysis method based on the base faces and their blending ratio is proposed. The seven base faces were chosen as axes describing and analyzing arbitrary facial expression. We set up seven facial expressions such as, surprise, fear, anger, disgust, happiness, sadness, and expressionless as base faces. Facial expression was built by fitting generic 3D facial model to facial image. Two comparable methods, Genetic Algorithms and Simulated Annealing were used to search the blending ratio of base faces. The usefulness of the proposed method for facial expression analysis was proved by the facial expression synthesis results.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.179-188
• /
• 2008

In this paper, knowledge based text to facial sequence image system for interaction of lecturer and learner in cyber universities is studied. The system is defined by the synthesis of facial sequence image which is synchronized the lip according to the text information based on grammatical characteristic of hangul. For the implementation of the system, the transformation method that the text information is transformed into the phoneme code, the deformation rules of mouse shape which can be changed according to the code of phonemes, and the synthesis method of facial sequence image by using deformation rules of mouse shape are proposed. In the proposed method, all syllables of hangul are represented 10 principal mouse shape and 78 compound mouse shape according to the pronunciation characteristics of the basic consonants and vowels, and the characteristics of the articulation rules, respectively. To synthesize the real time facial sequence image able to realize the PC, the 88 mouth shape stored data base are used without the synthesis of mouse shape in each frame. To verify the validity of the proposed method the various synthesis of facial sequence image transformed from the text information is accomplished, and the system that can be applied the PC is implemented using the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.4
• /
• pp.614-623
• /
• 1994

Synthesizing speech and facial images is necessary for human interface that man and machine converse naturally as human do. The target of this paper is synthesizing the facial images. In synthesis of the facial images a three-dimensional (3-D) shape model of the face is used for realizating the facial expression variations and the lip shape variations. The various facial expressions and lip shapes harmonized with the syllables are synthesized by deforming the three-dimensional model on the basis of the facial muscular actions. Combications with the consonants and the vowels make 14.364 syllables. The vowels dominate most lip shapes but the consonants do a part of them. For determining the lip shapes, this paper investigates all the syllables and classifies the lip shapes pattern according to the vowels and the consonants. As the results, the lip shapes are classified into 8 patterns for the vowels and 2patterns for the consonants. In advance, the paper determines the synthesis rules for the classified lip shape patterns. This method permits us to obtain the natural facial image with the various facial expressions and lip shape patterns.

• Proceedings of the Korea Contents Association Conference
• /
• 2011.05a
• /
• pp.51-52
• /
• 2011

We introduce a novel complete framework for contructing realistic facial animations given just one facial photo as an input in this paper. Our approach is carried on in 2D photo spacem not 3D space. Moreover, we utilize computer vision-based technique (digital matting) as well as conventional image processing methods (image warping and texture synthesis) for expressing more realistic facial animations. Simulated results show that our scheme produces high quality facial animations very efficiently.

• Korean Journal of Cognitive Science
• /
• v.14 no.1
• /
• pp.41-50
• /
• 2003

We tested the capability of the pleasure and arousal dimension-based facial expression synthesis system and proposed the most effective interface for it. First, we tried to confirm the adequateness of the dimensional model as a basic structure of the internal states for the system. Fer it, subjects compared the 17 facial expressions on the two axes. The results validated the fundamental hypothesis of the system. Second, we chose 21 representative expressions from the system to test its performance and had subjects rate their similarities. We analyzed these data using multidimensional scaling methods and these results verified the system's reliability. Third, we compared the efficiencies of two interfaces -coordinate values and slide bars- to find the most suitable interface for the system. Subjects synthesise 25 facial expressions with each interface of it. The results showed that the visualization of two dimensional values into Cartesian coordinate is more stable as an input display of facial expression synthesis system based on dimensions.