• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.711-720
• /
• 2012

In this paper, we introduce the implementation of driver fatigue monitering system and its result. Input video device is selected commercially available web-cam camera. Haar transform is used to face detection and adopted illumination normalization is used for arbitrary illumination conditions. Facial image through illumination normalization is extracted using Haar face features easily. Eye candidate area through illumination normalization can be reduced by anthropometric measurement and eye detection is performed by PCA and Circle Mask mixture model. This methods achieve robust eye detection on arbitrary illumination changing conditions. Drowsiness state is determined by the level on illumination normalize eye images by a simple calculation. Our system alarms and operates seatbelt on vibration through controller area network(CAN) when the driver's doze level is detected. Our algorithm is implemented with low computation complexity and high recognition rate. We achieve 97% of correct detection rate through in-car environment experiments.

• Steel and Composite Structures
• /
• v.44 no.1
• /
• pp.65-79
• /
• 2022

The main goal of this paper is to study the vibration of damaged core laminated annular plates with FG face sheets based on a three-dimensional theory of elasticity. The structures are made of a damaged isotropic core and two external face sheets. These skins are strengthened at the nanoscale level by randomly oriented Carbon nanotubes (CNTs) and are reinforced at the microscale stage by oriented straight fibers. These reinforcing phases are included in a polymer matrix and a three-phase approach based on the Eshelby-Mori-Tanaka scheme and on the Halpin-Tsai approach, which is developed to compute the overall mechanical properties of the composite material. In this study the effect of microcracks on the vibrational characteristic of the sandwich plate is considered. In particular, the structures are made by an isotropic core that undergoes a progressive uniform damage, which is modeled as a decay of the mechanical properties expressed in terms of engineering constants. These defects are uniformly distributed and affect the central layer of the plates independently from the direction, this phenomenon is known as "isotropic damage" and it is fully described by a scalar parameter. Three complicated equations of motion for the sectorial plates under consideration are semi-analytically solved by using 2-D differential quadrature method. Using the 2-D differential quadrature method in the r- and z-directions, allows one to deal with sandwich annular plate with arbitrary thickness distribution of material properties and also to implement the effects of different boundary conditions of the structure efficiently and in an exact manner. The fast rate of convergence and accuracy of the method are investigated through the different solved examples. The sandwich annular plate is assumed to have any arbitrary boundary conditions at the circular edges including simply supported, clamped and, free. Several parametric analyses are carried out to investigate the mechanical behavior of these multi-layered structures depending on the damage features, through-the-thickness distribution, and boundary conditions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.95-101
• /
• 2006

A face detection plays an important role in face recognition, video surveillance, and human computer interaction. In this paper, we propose a progressive threshold method to detect human faces in real time. The consecutive face images are acquired from camera and transformed into YCbCr color space images. The skin color of the input images are separated using a skin color filter in the YCbCr color space and some candidated face areas are decided by connected component analysis. The intensity equalization is performed to avoid the effect of many circumstances and an arbitrary threshold value is applied to get binary images. The eye area can be detected because the area is clearly distinguished from others in the binary image progressive threshold method searches for an optimal eye area by progressively increasing threshold from low values. After progressive thresholding, the eye area is normalized and verified by back propagation algorithm to finalize the face detection.

• Journal of Broadcast Engineering
• /
• v.13 no.3
• /
• pp.339-349
• /
• 2008

We present a novel method to estimate the light source direction and relight a face texture image of a single 3D model under arbitrary unknown illumination conditions. We create a virtual irradiance sphere to detect the light source direction from a given illuminated texture image using both normal vector mapping and weighted bilinear interpolation. We then induce a relighting equation with estimated ambient and diffuse coefficients. We provide the result of a series of experiments on light source estimation, relighting and face recognition to show the efficiency and accuracy of the proposed method in restoring the shading and shadows areas of a face texture image. Our approach for face relighting can be used for not only illuminant invariant face recognition applications but also reducing visual load and Improving visual performance in tasks using 3D displays.

• Korean Journal of Computational Design and Engineering
• /
• v.2 no.1
• /
• pp.28-34
• /
• 1997

A swept volume is a useful tool for solving various types of interference problems. Previous works have concentrated on sweeping an object along an arbitrary path, that results in complex algorithms. This paper concerns the volume swept by translating an object along a linear path. After analyzing the structure of the swept volume, we present an incremental algorithm for constructing a swept volume. Our algorithm takes O(n/sup 2/ *.alpha.(n)+T/sub c/) time where n is the number of vertices in the original object and T/sub c/ is time for handling face cycles.

• Journal of computational fluids engineering
• /
• v.11 no.1 s.32
• /
• pp.8-15
• /
• 2006

The existing approximations of diffusion flux in unstructured cell-centered finite volume methods are examined in detail with each other and clarified to have indefinite expressions in several respects. A new numerical approximation of diffusion flux at cell face center is then proposed, which is second-order accurate even on irregular grids and may be easily implemented in CFD code using cell-centered finite volume method with unstructured grids composed of arbitrary convex polyhedral shape.

• Structural Engineering and Mechanics
• /
• v.12 no.4
• /
• pp.363-376
• /
• 2001

Sandwich plates are widely used in lightweight design due to their high strength and stiffness to weight ratio. Due to the heterogeneous structure of sandwich plates, they can exhibit local instabilities (wrinkling), which lead to a sudden loss of stiffness in the structure. This paper presents an analytical solution to the wrinkling problem of sandwich plates. The solution is based on the Rayleigh-Ritz method, by assuming an appropriate deformation field. In contrast to the other approaches up to now, this model takes arbitrary and different orthotropic face layers, finite core thickness and orthotropic core material into account. This approach is the first to cover the wrinkling of unsymmetric sandwiches and sandwiches composed of orthotropic FRP face layers, which are most common in advanced lightweight design. Despite the generality of the solution, the computational effort is kept within bounds. The results have been verified using other analytical solutions and unit cell 3D FE calculations.

• Steel and Composite Structures
• /
• v.28 no.5
• /
• pp.541-557
• /
• 2018

This paper presents the influence of carbon nanotubes (CNTs) waviness and aspect ratio on the vibrational behavior of functionally graded nanocomposite sandwich annular sector plates resting on two-parameter elastic foundations. The carbon nanotube-reinforced (CNTR) sandwich plate has smooth variation of CNT fraction along the thickness direction. The distributions of CNTs are considered functionally graded (FG) or uniform along the thickness and their mechanical properties are estimated by an extended rule of mixture. In this study, the classical theory concerning the mechanical efficiency of a matrix embedding finite length fibers has been modified by introducing the tube-to-tube random contact, which explicitly accounts for the progressive reduction of the tubes' effective aspect ratio as the filler content increases. Effects of CNT distribution, volume fraction, aspect ratio and waviness, and also effects of Pasternak's elastic foundation coefficients, sandwich plate thickness, face sheets thickness and plate aspect ratio are investigated on the free vibration of the sandwich plates with wavy CNT-reinforced face sheets. The study is carried out based on three-dimensional theory of elasticity and in contrary to two-dimensional theories, such as classical, the first- and the higher-order shear deformation plate theories, this approach does not neglect transverse normal deformations. The sandwich annular sector plate is assumed to be simply supported in the radial edges while any arbitrary boundary conditions are applied to the other two circular edges including simply supported, clamped and free.