• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.675-682
• /
• 2004

With the five-day workweek system in bank and the increased usage of ATM(Automatic Toller Machine), it is required that the financial crime using stolen credit card should be prevented. Though a CCTV camera is usually installed in near ATM, an intelligent criminal can cheat it disguising himself with sunglass or mask. In this paper, we propose facial feature verification system which can detect whether the user's face can be Identified or not, using image processing algorithm and SVM(Support Vector Machine). Experimental results show that FAR(Error Rate for accepting a disguised man as a non-disguised one) is 1% and FRR(Error Rate for rejecting a normal/non-disguised man as a disguised one) is 2% for training data. In addition, it shows the FAR of 2.5% and the FRR of 1.43% for test data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.9
• /
• pp.901-908
• /
• 2016

Edge is the basic characteristic of image, edge detection is very important in image processing applications and computer vision area. Many studies are being performed to detect these edges by domestic and foreign researchers. The conventional edge detection methods such as Roberts, Sobel, Prewitt, and Laplacian etc, which are using a fixed value of mask are widely used and morphological gradient which uses dilation and erosion among morphology process techniques is also widely used. But these methods does not detect edges well in the diagonal direction or gradually changing image parts. Accordingly, in this paper, the modified top-hat and bottom-hat transform algorithms which are detecting edges well in the parts of diagonal direction or gradually changing image are proposed. The proposed algorithms present the detected edge images compared with the conventional methods and are evaluated performance by using cosine similarity.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.901-911
• /
• 2009

In this paper, we propose a construction technique of two-level composite gradient map to automatically track a face with large movement in successive frames. Our method is composed of three main steps. First, the gradient maps with two-level resolution are generated for fast convergence of active contour. Second, to recognize the variations of face between successive frames and remove the neighbor background, weighted composite gradient map is generated by combining the composite gradient map and difference mask of previous and current frames. Third, to prevent active contour from converging local minima, the energy slope is generated by using closing operation. In addition, the fast closing operation is proposed to accelerate the processing time of closing operation. For performance evaluation, we compare our method with previous active contour model-based face tracking methods using a visual inspection, robustness test and processing time. Experimental results show that our method can effectively track the face with large movement and robustly converge to the optimal position even in frames with complicated background.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1222-1230
• /
• 2015

Segmentation of the anterior cruciate ligament (ACL) in knee MRI remains a challenging task due to its inhomogeneous signal intensity and low contrast with surrounding soft tissues. In this paper, we propose a multi-atlas-based segmentation of the ACL in knee MRI with locally-aligned probabilistic atlas (PA) in an iterative graph cuts framework. First, a novel PA generation method is proposed with global and local multi-atlas alignment by means of rigid registration. Second, with the generated PA, segmentation of the ACL is performed by maximum-aposteriori (MAP) estimation and then by graph cuts. Third, refinement of ACL segmentation is performed by improving shape prior through mask-based PA generation and iterative graph cuts. Experiments were performed with a Dice similarity coefficients of 75.0%, an average surface distance of 1.7 pixels, and a root mean squared distance of 2.7 pixels, which increased accuracy by 12.8%, 22.7%, and 22.9%, respectively, from the graph cuts with patient-specific shape constraints.

• Journal of Korean society of Dental Hygiene
• /
• v.11 no.1
• /
• pp.29-38
• /
• 2011

Objectives : The purpose of this study was to survey the awareness of methicillin -resistant Staphylococcus aureus(MRSA) among dental hygiene students in Yeungnam South Korea. Also the knowledge of infection control and infection diseases was surveyed. Methods : The subjects in this study were 213 dental hygiene students in three different colleges in Yeungnam. This study was conducted by using the self-reported questionnaire. Results : In the first, most of the students(86.9%) did not know about MRSA and 85.7% of them got the information in the college. Secondly, the awareness of infectious disease according to infection control education didn't have statistically significant difference(p>0.05). In the third, the infection control attitude level that the gowns should be changed after the treatment of infectious patients was scored lower than the others questions. on the other hand, the level of 'The use of high vacuum suction', 'The change of wet mask', 'The history taking of infectious disease' was scored higher. Finally, the attitude level according to grade and clinical training had statistically significant difference(p<0.05). But the infection control education had not affected significantly(p>0.05). Conclusions : Despite the infection control education and clinical training, the awareness was found insufficient in infectious diseases and MRSA. Therefore, it should be strengthen that the dental hygiene students were more educated about infection control at college course before clinical training, and especially the danger of MRSA was more.

• Journal of Satellite, Information and Communications
• /
• v.7 no.3
• /
• pp.1-7
• /
• 2012

In this paper, we was performed the interference analysis to determine an optimal coexisting criteria for the european digital video broadcasting service (DVB-T2) and the IMT-advanced LTE based TV Band Device (TVBD). The TVBD was equipped with the spectrum cognition method. To this end, we set the various transmission parameters, that includes the emission and blocking mask, antenna height and gain, transmission power and bandwidth, channel model etc. Based on this parameters, we were calculated the allowable transmit power, the number of TVBD and the change in probability of interference for the TVBD user operating in the adjacent channels of the DVB-T2 user. Also this paper presents how many TVBD users can sharing with DVB-T2 for spectral cognition performance.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.2 s.332
• /
• pp.75-80
• /
• 2005

In this paper, 2-stage power amplifier has been designed for 5.8GHz wireless LAN application. The power amplifier PldB output power has 21.6dBm at 5.8GHz frequency. Also the power amplifier shows 17.6dB gain and -17.8dB input return loss at 5.725GHz to 5.825GHz. The OFDM modulation and transmission block have been modeled in order to analyse the relationship between the power amplifier distortion and output ACPR for the IEEE 802.11a wireless LAN. The nonlinear characteristic of the power amplifier has been modeled as AM-to-AM and AM-to-PM using the behavioral model, and the output spectrum is analysed with the phase distortion variation. Also, amplifier back-off value from PldB to satisfy the required IEEE 802.11a standard spectrum mask has been simulated with phase distortion, and the simulation data have been compared to the measurement result collected by using the pre-distortion technique.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.2 no.4
• /
• pp.259-267
• /
• 2002

We present a novel 3D fabrication method with single X-ray process utilizing an X-ray mask in which a micro-actuator is integrated. An X-ray absorber is electroplated on the shuttle mass driven by the integrated micro-actuator during deep X-ray exposures. 3D microstructures are revealed by development kinetics and modulated in-depth dose distribution in resist, usually PMMA. Fabrication of X-ray masks with integrated electrothermal xy-stage and electrostatic actuator is presented along with discussions on PMMA development characteristics. Both devices use $20-\mu\textrm{m}$-thick overhanging single crystal Si as a structural material and fabricated using deep reactive ion etching of silicon-on-insulator wafer, phosphorous diffusion, gold electroplating, and bulk micromachining process. In electrostatic devices, $10-\mu\textrm{m}-thick$ gold absorber on $1mm{\times}1mm$ Si shuttle mass is supported by $10-\mu\textrm{m}-wide$, 1-mm-long suspension beams and oscillated by comb electrodes during X-ray exposures. In electrothermal devices, gold absorber on 1.42 mm diameter shuttle mass is oscillated in x and y directions sequentially by thermal expansion caused by joule heating of the corresponding bent beam actuators. The fundamental frequency and amplitude of the electrostatic devices are around 3.6 kHz and $20\mu\textrm{m}$, respectively, for a dc bias of 100 V and an ac bias of 20 VP-P (peak-peak). Displacements in x and y directions of the electrothermal devices are both around $20{\;}\mu\textrm{m}$at 742 mW input power. S-shaped and conical shaped PMMA microstructures are demonstrated through X-ray experiments with the fabricated devices.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.175-182
• /
• 2017

Noises are usually generated by various external causes and low quality devices in image data acquisition and recording as well as by channel interference in image transmission. Since these noise signals result in the loss of information, subsequent image processing is subject to the corruption of the original image. In general, image processing is performed in the mixed noise environment where common types of noise, known to be Gaussian and impulse, are present. This study proposes an iterative weighted mean filter for reducing mixed type of noise. Impulse noise pixels are first turned off in the input image, then $3{\times}3$ sliding window regions are processed by replacing center pixel with the result of weighted mean mask operation. This filtering processes are iterated until all the impulse noise pixels are replaced. Applied to images corrupted by Gaussian noise with ${\sigma}=10$ and different levels of impulse noise, the proposed filtering method improved the PSNR by up to 12.98 dB, 1.97 dB, 1.97 dB respectively, compared to SAWF, AWMF, MMF when impulse noise desities are less than 60%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.121-126
• /
• 2004

An efficient multi face detection technique is proposed based on hierarchical context-free attention operators in which multiple faces are efficiently detected from a noisy and complex background. A noise-tolerant generalized symmetry transform (NTSGT) is applied hierarchically, as a context free attention operator, to the input pyramidal image for the high speed global location of the regions of face candidates (ROFCs) with a single mask. For the face verification, local NTGST is applied within each ROFC to confirm the existence of the detailed facial features. First, by globally applying NTGST which introduces the average pyramid method and focusing to the input image with complex background, ROFCs with recognizable resolution are detected robustly. Morphological operations are applied only to the each detected ROFCs to emphasize the facial features like eyes and lips. Then, eyes are detected by locally appling NTGST to the ROFCs and only faces are detected by verifying the existence of the geometrical features of the faces relatively to the location of eyes. The experimental results show that the proposed method can efficiently detect multiple faces from a noisy or complex background with 93.5% detection rate.