• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.85-92
• /
• 2021

In a face, there is much information of person's identity. Because of this property, various tasks such as expression recognition, identity recognition and deepfake have been actively conducted. Most of them use the exact frontal view of the given face. However, various directions of the face can be observed rather than the exact frontal image in real situation. The profile (side view) lacks information when comparing with the frontal view image. Therefore, if we can generate the frontal face from other directions, we can obtain more information on the given face. In this paper, we propose a combined style model based the conditional generative adversarial network (cGAN) for generating the frontal face from multi-view images that consist of characteristics that not only includes the style around the face (hair and beard) but also detailed areas (eye, nose, and mouth).

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.239-244
• /
• 2016

Mugshot face images, routinely collected by police, usually contain both frontal and profile views. Existing automated face recognition methods exploited mugshot databases by enlarging the gallery with synthetic multi-view face images generated from the mugshot face images. This paper, instead, proposes to match the query arbitrary view face image directly to the enrolled frontal and profile face images. During matching, the 3D face shape model reconstructed from the mugshot face images is used to establish corresponding semantic parts between query and gallery face images, based on which comparison is done. The final recognition result is obtained by fusing the matching results with frontal and profile face images. Compared with previous methods, the proposed method better utilizes mugshot databases without using synthetic face images that may have artifacts. Its effectiveness has been demonstrated on the Color FERET and CMU PIE databases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12C
• /
• pp.984-994
• /
• 2010

Pose variation is a critical problem in face recognition. Three-dimensional(3D) face recognition techniques have been proposed, as 3D data contains depth information that may allow problems of pose variation to be handled more effectively than with 2D face recognition methods. This paper proposes a pose-normalized 3D face modeling method that translates and rotates any pose angle to a frontal pose using a plane fitting method by Singular Value Decomposition(SVD). First, we reconstruct 3D face data with stereo vision method. Second, nose peak point is estimated by depth information and then the angle of pose is estimated by a facial plane fitting algorithm using four facial features. Next, using the estimated pose angle, the 3D face is translated and rotated to a frontal pose. To demonstrate the effectiveness of the proposed method, we designed 2D and 3D face recognition experiments. The experimental results show that the performance of the normalized 3D face recognition method is superior to that of an un-normalized 3D face recognition method for overcoming the problems of pose variation.

• Journal of Korea Multimedia Society
• /
• v.7 no.12
• /
• pp.1692-1699
• /
• 2004

Many researchers have developed various techniques for detection of human faces in ordinary still images. Face detection is the first imperative step of human face recognition systems. The two main problems of human face detection are how to cutoff the running time and how to reduce the number of false positives. In this paper, we present frontal and near-frontal face detection algorithm in still gray images using a thick edge image and neural network. We have devised a new filter that gets the thick edge image. Our overall scheme for face detection consists of two main phases. In the first phase we describe how to create the thick edge image using the filter and search for face candidates using a whole face detector. It is very helpful in removing plenty of windows with non-faces. The second phase verifies for detecting human faces using component-based eye detectors and the whole face detector. The experimental results show that our algorithm can reduce the running time and the number of false positives.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1013-1014
• /
• 2008

In this paper, we propose a new method of generating 3D face by using single frontal face image and 3D generic face model. By using active appearance model (AAM), the control points among facial feature points were localized in the 2D input face image. Then, the transform parameters of 3D generic face model were found to minimize the error between the 2D control points and the corresponding 2D points projected from 3D facial model. Finally, by using the obtained model parameters, 3D face was generated. We applied this 3D face to 3D game framework and found that the proposed method could make a realistic 3D face of game user.

• The Journal of Korean Medicine
• /
• v.30 no.6
• /
• pp.86-95
• /
• 2009

Objectives: This study aimed to examine the difference of external appearance measurements in subjects of different regional lineages as subgroups within the Tae-eumin Sasang grouping. Methods: We chose 51 Tae-eumin subjects diagnosed by Korean Sasang constitutional medical doctors aided by voice analysis. The subjects were divided into two groups, the northern and southern lineages, by an expert on facial characteristics of the two lineages. We took pictures of their frontal and lateral views by Martin's method, measured projected length of face with the Facial Feature Measurement Program, and analyzed anthropometric facial differences between the northern and southern types. Results: Results show differences between the northern and southern types. First, the northern type of face has bigger measurements than the southern type on the frontal face. Second, the northern type of face has higher measurements of "height", which means distance from pupil to a specific measurement point, than the southern type on the frontal face. Third, on the frontal face, the northern and southern types have differences with respect to eyebrow, point of sellion, and eye. Fourth, on the side face, the northern and southern types have differences in lip, mandible and ear. Conclusions: We found our anthropometric facial measurements of the northern and southern lineages to be in accordance with previous literature. Knowledge of the differences between the northern and southern lineages can be a hint in constitutional diagnosis when differentiation is clinically confusing.

• Journal of Korea Multimedia Society
• /
• v.15 no.5
• /
• pp.606-614
• /
• 2012

Face detection using AdaBoost algorithm is one of the fastest and the most robust face detection algorithm so many improvements or extensions of this method have been proposed. However, almost all previous approaches deal with only frontal face and suffer from limited discriminant capability for inclined face because these methods apply the same features for both frontal and inclined face. Also conventional approaches for detecting inclined face which apply frontal face detecting method to inclined input image or make different detectors for each angle require heavy computational complexity and show low detection rate. In order to overcome this problem, a method for detecting inclined face using JointBoost is proposed in this paper. The computational and sample complexity is reduced by finding common features that can be shared across the classes. Simulation results show that the detection rate of the proposed method is at least 2% higher than that of the conventional AdaBoost method under the learning condition with the same iteration number. Also the proposed method not only detects the existence of a face but also gives information about the inclined direction of the detected face.

• Archives of Plastic Surgery
• /
• v.37 no.3
• /
• pp.271-276
• /
• 2010

Purpose: The purpose is to present an useful and simple surgical method to improve the aging of upper third face in patients with high frontal hairline as well as low frontal hairline. Methods: Forty eight female patients were treated with subcutaneous forehead lift using an anterior hairline incision over 14 years. This surgical technique is performed under direct vision utilizing a beveled incision made 4 to 5 mm into the anterior hairline with subcutaneous dissection, which is continued near to eyebrow, sometimes extended to supraorbital rim to remove corrugator and procerus muscles. In patients with high frontal hairline, excess forehead skin anterior to incision line is removed. On the contrary in the patients with low frontal hairline, scalp posterior to incision line is removed. Results: This technique provided constant and good results with the forty six patients, who were satisfied with eyebrow elevation and removal of wrinkles in forehead and glabellar region. However two patients were undercorrected, and focal alopecia developed in another two patients. One patient complained of pruritus over one year, but subsided spontaneously without any treatment. Temporary paresthesia developed in the forehead and frontal scalp of all cases after operation but permanent sensory loss never occurred in all the patients. Conclusion: Subcutaneous forehead lift using an anterior hairline incision is suggested to be one of the effective surgical methods to improve the aging of upper third face in the patients with high frontal hairline as well as low frontal hairline.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2C
• /
• pp.194-199
• /
• 2009

This paper proposes a face detection algorithm that uses geometrical information on face and hair region. This information that face adjoins hair regions can be the important one for face detection. It is also kept in images with frontal, rotated and lateral face. The face candidates are founded by the analysis of skin regions after detecting the skin and hair color regions in an image. Next, the intersected lesions between face candidates and hair's are created. Finally, the face candidates that include the subsets of these regions turn out to be face. Experimental results showed the high detection rates for frontal and lateral faces as well as faces geometrically distorted.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.6C
• /
• pp.570-576
• /
• 2005

Recognition of posed face is one of the most challenging problems in the field of face recognition. In this paper, as a preprocessing step for recognizing such faces, a method to transform non-frontal face images into frontal face images is proposed. The linear relationship between eigenfaces is utilized to obtain a pose transform matrix. The proposed method is verified with a well-known face recognition algorithm based on PCA/LDA. Compared to the conventional algorithm applied to the original posed face images, our experimental results indicated that the proposed method contributes to improve the recognition rate of such faces by $20\%$.