• Journal of Multimedia Information System
• /
• 제7권4호
• /
• pp.239-248
• /
• 2020

The performance of the facial recognition system is determined by many technical factors. Further, most of the technical factors have been realized or are still in continued research. The recognition rate has a great influence on performance not only by technical factors but also by other factors. However, researchers are trying to improve the recognition rate by focusing only on technical factors. The mechanism of recognizing is to compare a face image obtained by photography to an already stored face image and determine the score of the similarity. However, if the photographed image is damaged by external light, even a system with a good algorithm will fail to recognize it. Therefore, it is important to prevent the disturbance of light entering from the outside, so it should be blocked, but the camera will not work without light. Thus, it is proposed that a method to secure the external light but block the disturbance of light that affects photography. A method of blocking disturbance light is to use a polarization filter. There are three polarization methods: circular polarization, linear polarization, and elliptical polarization. In this paper, an experiment was performed to overcome disturbance of light using only a circularly polarized filter. In addition, a lighting system that reproduces disturbance light was provided for the experiment, and light of varying intensities and angles was installed to affect the face recognition camera. As a result of actual application, it was determined that a very improved recognition performance in various disturbance light environments.

• Journal of Korea Multimedia Society
• /
• 제14권4호
• /
• pp.494-503
• /
• 2011

In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

• The Korean Journal of Pain
• /
• 제13권2호
• /
• pp.187-190
• /
• 2000

Background: From our clinical experience, there were some problems in paratracheal stellate ganglion block at 6th cervical level (C 6 SGB), for example, lesser change in blood flow of the upper extremity and more occurrence of hoarseness. This study was undertaken to compare the various effectiveness of C 6 SGB and paratracheal stellate ganglion block at 7th cervical level (C 7 SGB). Methods: Forty patients were equally divided into 2 groups. In the Group I, patients were undertaken C 6 SGB with 0.25% bupivacaine 6 mL and in the Group II, patients were undertaken C 7 SGB with 0.25% bupivacaine 6mL. The skin temperature of index finger was measured before and after SGB and the warm sensation on face and upper extremity, hoarseness and upper extremity paralysis were studied. Results: The skin temperature of index finger was increased significantly from $33.95{\pm}0.89^{\circ}C$ to $34.51{\pm}0.90^{\circ}C$ in the Group I and from $33.94{\pm}0.82^{\circ}C$ to $35.38{\pm}0.66^{\circ}C$ in the Group II (P<0.05) The increase of skin temperature of index finger after procedure was $0.56{\pm}0.09^{\circ}C$ in the Group I and $1.44{\pm}0.02^{\circ}C$ in the Group II. The increase of skin temperature of index finger in the Group II was more statistically significant than Group I (P<0.05). The occurance of hoarseness in the Group II was significantly less than in the Group I. There was no significant difference in warm sensation on face and upper extremity and paralysis of upper extremity in both Groups. Conclusions: C 7 SGB showed better sympathetic block effect on upper extremity than C 6 SGB and hoarseness did not occur in C 7 SGB.

• Tunnel and Underground Space
• /
• 제31권6호
• /
• pp.415-427
• /
• 2021

This technical report briefly introduced the rock cutting splitting method under development. This method is a method of excavating the rock by splitting the block after the rock cutting process. After designing the cutting geometry of the rock face, the chisel is press-fitted to remove the rock block. At this time, when the cutting block is properly designed, the tensile crack propagates smoothly at the bottom of the rock block. An analytical solution was devised to estimate the indentation force required for splitting rock blocks using fracture toughness mode 1 required for tensile crack growth. The impact force of the hydraulic breaker of the excavator was analyzed, and the grade of the excavator that can be constructed according to the rock block design geometry was analyzed.

• Korea-Australia Rheology Journal
• /
• 제19권4호
• /
• pp.227-232
• /
• 2007

The use of various shearing apparatuses to study the phase behavior of poly(styrene-b-isoprene) diblock copolymer micelles is described. A DMTA rheometer was modified so that one can apply oscillatory shear and obtain the scattering pattern along the shear gradient direction. A cone and plate shear cell was designed to access scattering along the shear vorticity direction, and both oscillatory and steady shear can be applied. The most popular way to employ steady shear on relatively low viscosity fluids is to use a Couette cell, because a high shear rate can be readily achieved without disturbing the sample by overflow. In this work, oscillatory shear was used to obtain a single crystal-like scattering pattern, and thereby to examine the mechanism of the thermotropic transition between face-centered cubic (fcc) and body-centered cubic (bcc) lattices. By applying the steady shear, the response of the fcc lattices to various shear rates is discussed.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.227-230
• /
• 2002

In this paper we concentrate on overall direction of the gaze based on a head pose for human computer interaction. To decide a gaze direction of user in a image, it is important to pick up facial feature exactly. For this, we binarize the input image and search two eyes and the mouth through the similarity of each block ( aspect ratio, size, and average gray value ) and geometric information of face at the binarized image. We create a imaginary plane on the line made by features of the real face and the pin hole of the camera to decide the head orientation. We call it the virtual facial plane. The position of a virtual facial plane is estimated through projected facial feature on the image plane. We find a gaze direction using the surface normal vector of the virtual facial plane. This study using popular PC camera will contribute practical usage of gaze tracking technology.

• Macromolecular Research
• /
• 제16권1호
• /
• pp.51-56
• /
• 2008

Spherical micelles of poly(styrene-b-isoprene) (SI) diblock copolymers in selective solvents have been reported to pack onto either face-centered cubic (fcc) or body-centered cubic (bcc) lattices. The selection rule for fcc and bcc lattices has been understood in terms of the intermicellar potentials, and they have been quantified using the ratio of the corona layer thickness to the core radius, $L/R_c$, as suggested by McConnell and Gast. In order to test the validity of the McConnell-Gast criterion, this study compared the $L/R_c$ values from various solutions i.e. nine SI copolymers in several different selective solvents. The McConnell-Gast criterion was not found to be a determining factor, even though it could explain the fcc/bcc selection qualitatively. From the phase diagrams, the transition between fcc and bcc phases was also considered as a function of concentration and temperature, and their physical mechanisms are discussed based on the recent mean-field calculation reported by Grason.

• IE interfaces
• /
• 제13권4호
• /
• pp.591-598
• /
• 2000

In this paper, an efficient algorithm is proposed to find parting lines(PL) and generate parting surfaces(PS) for an injection mold design. We used a Face-Edge Graph which can be made by B-rep information of solid model. The graph is useful for finding the peripheral-loop edges for PL and the inner-loop edges for hole-patch. The PS can be generated automatically by selecting pre-defined direction lines. We can create a core and cavity molds by trimming the raw stock block with the PS and the upper/lower faces of a product model. We implemented proposed method with Unigraphics API functions and C language, and tesed on Unigraphics V15.

• Journal of KIISE:Software and Applications
• /
• 제28권11호
• /
• pp.855-863
• /
• 2001

We propose an image alignment algorithm based on variable-sized blocks of cylindrical prototype model to generate a face texture for a realistic 3D face model. This is a block matching algorithm which aligns 2D images of a 3D cylindrical model using th correlation between them. While matching blocks, it does not use same sized blocks with considering a curvature of 3D model. And we make a texture of aligned images using a technique of image mosaic. For this purpose, we stitch them with assigning linear weights according to the overlapped region and using the cross-dissolve technique.

• Journal of Korea Multimedia Society
• /
• 제13권1호
• /
• pp.66-75
• /
• 2010

We proposed an occupant sensing system using single video camera and ultrasonic sensor for the advanced airbag. To detect the occupant form and the face position in real-time, we used the skin color and motion information. We made the candidate face block image using the threshold value of the color difference signal corresponding to skin color and difference value of current image and previous image of luminance signal to gel motion information. And then it detects the face by the morphology and the labeling. In case of night without color and luminance information, it detects the face by using the threshold value of the luminance signal get by infra-red LED instead of the color difference signal. To evaluate the performance of the proposed occupant detection system, it performed various experiments through the setting of the IEEE camera, ultrasonic sensor, and infra-red LED in vehicle jig.