• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.31-38
• /
• 2023

This paper introduces a real-time face swapping system that enables video influencers to swap their faces with arbitrary generated face images of their choice. The system is implemented as a Django-based server that uses a REST request to communicate with the generative model,specifically the pretrained stable diffusion model. Once generated, the generated image is displayed on the front page so that the influencer can decide whether to use the generated face or not, by clicking on the accept button on the front page. If they choose to use it, both their face and the generated face are sent to the landmark extraction module to extract the landmarks, which are then used to swap the faces. To minimize the fluctuation of landmarks over time that can cause instability or jitter in the output, a temporal filtering step is added. Furthermore, to increase the processing speed the system works on a reduced set of the extracted landmarks.

• 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.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.342-347
• /
• 2008

Face tracking and recognition are difficult problems because the face is a non-rigid object. If the system tries to track or recognize the unknown face continuously, it can be more hard problems. In this paper, we propose the method to track and to recognize the face of the unknown person on video sequences using linear combination of nonlinear manifold models that is constructed in the system. The arbitrary input face has different similarities with different persons in system according to its shape or pose. Do we can approximate the new nonlinear manifold model for the input face by estimating the similarities with other faces statistically. The approximated model is updated at each frame for the input face. Our experimental results show that the proposed method is efficient to track and recognize for the arbitrary person.

• Honam Mathematical Journal
• /
• v.38 no.2
• /
• pp.425-433
• /
• 2016

In this paper, we study face and flag information of a generalized wedge of two polytopes over a face. In particular, we provide the explicit formula for the cd-index of the wedge of a polytope and a one-dimensional simplex over an arbitrary face.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.417-420
• /
• 2006

Detection of faces on still color images with arbitrary backgrounds is attempted in this paper. The newly proposed method is invariant to arbitrary background, number of faces, scale, orientation, skin color, and illumination through the steps of color clustering, cluster scanning, sub-block processing, face area detection, and face verification. The sub-block method makes the proposed method invariant to the size and the number of faces in the image. The proposed method does not need any pre-training steps or a preliminary face database. The proposed method may be applied to areas such as security control, video and photo indexing, and other automatic computer vision-related fields.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• Steel and Composite Structures
• /
• v.16 no.4
• /
• pp.389-415
• /
• 2014

This study deals with dynamic model of composite sandwich panels with functionally graded flexible cores under low velocity impacts of multiple large or small masses using a new improved higher order sandwich panel theory (IHSAPT). In-plane stresses were considered for the functionally graded core and face sheets. The formulation was based on the first order shear deformation theory for the composite face sheets and polynomial description of the displacement fields in the core that was based on the second Frostig's model. Fully dynamic effects of the functionally graded core and face-sheets were considered in this study. Impacts were assumed to occur simultaneously and normally over the top and/or bottom of the face-sheets with arbitrary different masses and initial velocities. The contact forces between the panel and impactors were treated as internal forces of the system. Nonlinear contact stiffness was linearized with a newly presented improved analytical method in this paper. The results were validated by comparing the analytical, numerical and experimental results published in the latest literature.

• Computers and Concrete
• /
• v.31 no.2
• /
• pp.163-171
• /
• 2023

Face gear transmission is widely used in aerospace shunt-confluence transmission system. Tooth wear is one of the main factors affecting its bearing transmission performance. Furthermore, the installation errors of face gear are inevitable. In order to study the wear mechanism of face gear tooth surface with installation errors, based on tooth contact analysis numerical method and Archard wear theory, the UMESHMOTION subroutine in ABAQUS is developed.Combining with Arbitrary Lagrangian-Eulerian adaptive mesh technology, the finite element mesh wear model of abraded face gear pair is established.The preprocessing conditions are set to generate the inp files.Then,the inp files for each corner are imported and batch processed in ABAQUS.The loading tooth contact problem at each rotation angle is solved and the load distribution coefficient among gear tooth, tooth root bending stress, tooth surface contact stress and loaded transmission error are obtained. Results show that the tooth root wear is the most serious and the wear at the pitch cone is close to 0.The wear law of tooth surface along tooth width direction is convex parabola and the wear law along tooth height direction is concave parabola.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.429-433
• /
• 1995

Compound solid is maded for specially fixed object. A number of compound soild are devided as a unit germetric solid. The special case of rotation about an arbitrary axis makes according selection modelfor transformation. View plane and View region are estiblished for back face removal. After back-face removal eachedge is checked for point of intersection. The designing of of fset surface id maded and tool-path gernerted on the part surface. In tersection point is checked among the offset surfaces. The paper used an efficient algorithm for generating tool paths to apply a notion view volume. Through machining experiments with a 3-axis machining centre, the adequacy of the analysis was confirmed.

• Journal of Korea Multimedia Society
• /
• v.24 no.9
• /
• pp.1279-1284
• /
• 2021

This paper addresses the task of transferring facial blendshape models to an arbitrary target face. Blendshape is a common method for the facial rig; however, production of blendshape rig is a time-consuming process in the current facial animation pipeline. We propose automatic blendshape facial rigging based on our blendshape transfer method. Our method computes the difference between source and target facial model and then transfers the source blendshape to the target face based on a deformation transfer algorithm. Our automatic method provides efficient production of a controllable digital human face; the results can be applied to various applications such as games, VR chating, and AI agent services.