• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.107-119
• /
• 1999

There is no authentic solution in a face detection problem though it is an important part of pattern recognition and has many diverse application fields. The reason is that there are many unpredictable deformations due to facial expressions, view point, rotation, scale, gender, age, etc. To overcome these problems, we propose an algorithm based on feature-based method, which is well known to be robust to these deformations. We detect a face by calculating a similarity between the formation of real face feature and candidate feature formation which consists of eyebrow, eye, nose, and mouth. In this paper, we use a steerable filter instead of general derivative edge detector in order to get more accurate feature components. We applied deformable template to verify the detected face, which overcome the weak point of feature-based method. Considering the low detection rate because of face detection method using whole input images, we design an adaptive skin-color filter which can be applicable to a diverse skin color, minimizing target area and processing time.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.144-152
• /
• 1996

In this paper, a pulse-mode digital multilayer neural network with a massively parallel yet compact and flexible network architecture is presented. Algebraicneural operations are replaced by stochastic processes using pseudo-random pulse sequences and simple logic gates are used as basic computing elements. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. A statistical model of the noise(error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Numerical character recognition problems are applied to the network to evaluate the network performance and to justify the validity of analytic results based on the developed statistical model. The network architectures are modeled in VHDL using the mixed descriptions of gate-level and register transfer level (RTL). Experiments show that the statistical model successfully predicts the accuracy of the operations performed in the network and that the character classification rate of the network is competitive to that of ordinary Back-Propagation networks.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.6
• /
• pp.800-807
• /
• 2016

We propose a fast algorithm using Extreme Contour Point (ECP) to detect the angle of rotated images, is implemented by rotation feature of one covered frame image that can be applied to correct the rotated images like in image processing for real time applications, while CORDIC is inefficient to calculate various points like high definition image since it is only possible to detect rotated angle between one point and the other point. The two advantages of this algorithm, namely compatibility to images in preprocessing by using Sobel edge process for pattern recognition. While the other one is its simplicity for rotated angle detection with cyclic shift of two $1{\times}n$ matrix set without complexity in calculation compared with CORDIC algorithm. In ECP, the edge features of the sample image of gray scale were determined using the Sobel Edge Process. Then, it was subjected to binary code conversion of 0 or 1 with circular boundary to constitute the rotation in invariant conditions. The results were extracted to extreme points of the binary image. Its components expressed not just only the features of angle ${\theta}$ but also the square of radius $r^2$ from the origin of the image. The detected angle of this algorithm is limited only to an angle below 10 degrees but it is appropriate for real time application because it can process a 200 degree with an assumption 20 frames per second. ECP algorithm has an O ($n^2$) in Big O notation that improves the execution time about 7 times the performance if CORDIC algorithm is used.

• Journal of Periodontal and Implant Science
• /
• v.47 no.3
• /
• pp.174-181
• /
• 2017

Purpose: Epitope spreading is a phenomenon in which distinct subdominant epitopes become major targets of the immune response. Heat shock protein (HSP) 60 from Porphyromonas gingivalis (PgHSP60) and peptide 19 from PgHSP60 (Pep19) are immunodominant epitopes in autoimmune disease patients, including those with periodontitis. It remains unclear whether Pep19 is a dominant epitope in subjects without periodontitis or autoimmune disease. The purpose of this study was to determine the epitope spreading pattern and verify Pep19 as an immunodominant epitope in healthy teenagers using dot immunoblot analysis. The patterns of epitope spreading in age-matched patients with type 1 diabetes mellitus (type 1 DM) and healthy 20- to 29-year old subjects were compared with those of healthy teenagers. Methods: Peptide from PgHSP60, Mycobacterium tuberculosis HSP60 (MtHSP60), and Chlamydia pneumoniae HSP60 (CpHSP60) was synthesized for comparative recognition by sera from healthy subjects and patients with autoimmune disease (type 1 DM). Dot immunoblot analysis against a panel of peptides of PgHSP60 and human HSP60 (HuHSP60) was performed to identify epitope spreading, and a densitometric image analysis was conducted. Results: Of the peptide from PgHSP60, MtHSP60, and CpHSP60, PgHSP60 was the predominant epitope and was most consistently recognized by the serum samples of healthy teenagers. Most sera from healthy subjects and patients with type 1 DM reacted more strongly with PgHSP60 and Pep19 than the other peptides. The relative intensity of antibody reactivity to Pep19 was higher in the type 1 DM group than in the healthy groups. Conclusions: Pep19 is an immunodominant epitope, not only in autoimmune disease patients, but also in healthy young subjects, as evidenced by their robust immunoreactivity. This result suggests that the Pep19-specific immune response may be an initiator that triggers autoimmune diseases.

• Sleep Medicine and Psychophysiology
• /
• v.3 no.2
• /
• pp.65-76
• /
• 1996

Natural sleep pattern and its physiology in childhood are much different from those in adulthood. Several aspects of clinical evaluation for sleepiness in childhood are more difficult than in adulthood. These difficulties are due to several factors. First, excessive sleepiness in childhood do not always develop functional impairments. Second, objective test such as MSLT may not be reliable since it is hard to be certain that the child understand instructions. Third, sleepiness in children is often obscured by irritability. paradoxical hyperactivity, or behavioral disturbances. Anseguently, careful clinical evaluation is needed for the sleepy children. Usual causes of sleepiness in children are the disorders that induce insufficient sleep such as sleep apnea syndrome, schedule disorder, underlying medical and psychiatric disorder, and so forth. After excluding such factors, we can diagnose the hypersomnic disorders such as narcolepsy, Kleine-Levin syndrome, and idiopathic central nervous system hypersomnia. Among the variety of those causes of sleepiness, I reviewed the clinical difference of narcolepsy and obstructive sleep apnea syndrome in childhood compared with in adulthood. Recognition of the childhood narcolepsy is difficult because even severely sleepy children often do not develop pathognomic cataplexy and associated REM phenomena until much later. Since childhood narcolepsy give srise to many psychological, academical problem. Practicers should be concerned about these aspects. Childhood obstructive sleep apnea syndrome is different from adult obstructive sleep apnea syndrome too. Several aspects such as pathophysiology. clinical feature, diagnostic criteria, complication, management, and prognosis differ from those in the adult syndrome. An important feature of childhood obstructive sleep apnea syndrome is the variety of severe complications such as behavioral disorders, cognitive impairment, cardiovascular symptoms, developmental delay, and ever death. Fortunately, surgical interventions like adenotosillectomy or UPPP are more effective for Childhood OSA than adult form. CPAP is a "safe, effective, and well-tolerated" treatment modality too. So if early detection and proper management of childhood OSA were done, the severe complication would be prevented or ever cured.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.3
• /
• pp.75-84
• /
• 2005

Since an unexpected fault of induction motor drive systems can cause serious troubles in many industrial applications, which the technique is required to diagnose faults of a voltage-fed PWM inverter for induction motor drives. The considered fault types are rectifier diodes, switching devices and input terminals with open-circuit faults, and the signal for diagnosis is derived from motor currents. The magnitude of dq-current trajectory is used for the feature extraction of a fault and PCA LDA are applied to diagnose. Also, we show results with respect to the execution time because of the possibility to use that a diagnosis software is embedded in the controllers of medium and small size induction motors drive for real-time diagnosis. After we performed various simulations for the fault diagnosis of the inverter, the usefulness of proposed algerian was verified.

• Journal of Yeungnam Medical Science
• /
• v.30 no.1
• /
• pp.10-16
• /
• 2013

Background: Toll-like receptors (TLRs) are well-known pattern recognition receptors. Among the 13 TLRs, TLR2 is the most known receptor for immune response. It activates mitogen-activated protein kinases (MAPKs), which are counterbalanced by MAPK phosphatases [MKPs or dual-specificity phosphatases (DUSPs)]. However, the regulatory mechanism of DUSPs is still unclear. In this study, the effect of a TLR2 ligand (TLR2L, Pam3CSK4) on DUSP4 expression in Raw264.7 cells was demonstrated. Methods: A Raw264.7 mouse macrophage cell line was cultured in Dulbecco's modified Eagle's medium supplemented with 10% fetal bovine serum and 1% antibiotics (100 U/mL penicillin and 100 g/mL streptomycin) at $37^{\circ}C$ in 5% $CO_2$. TLR2L (Pam3CSK4)-mediated DUSP4 expressions were confirmed with RT-PCR and western blot analysis. In addition, the detection of reactive oxygen species (ROS) was measured with lucigenin assay. Results: Pam3CSK4 induced the expression of DUSP1, 2, 4, 5 and 16. The DUSP4 expression was also increased by TLR4 and 9 agonists (lipopolysaccharide and CpG ODN, respectively). Pam3CSK4 also induced ERK1/2 phosphorylation and ROS production, and the Pam3CSK4-induced DUSP4 expression was decreased by ERK1/2 (U0126) and ROS (DPI) inhibitors. U0126 suppressed the ROS production by Pam3CSK4. Conclusion: Pam3CSK4-mediated DUSP4 expression is regulated by ERK1/2 and ROS. This finding suggests the physiological importance of DUSP4 in TLR2-mediated immune response.

• The Journal of the Korea Contents Association
• /
• v.11 no.10
• /
• pp.41-48
• /
• 2011

In feature selection, the selective evaluation scheme for Ant Colony Optimization(ACO) has recently been proposed, which reduces computational load by excluding unnecessary or less promising candidate solutions from the actual evaluation. Its superiority was supported by experimental results. However the experiment seems to be not statistically sufficient since it used only one dataset. The aim of this paper is to analyze convergence characteristics of the selective evaluation scheme and to make the conclusion more convincing. We chose three datasets related to handwriting, medical, and speech domains from UCI repository whose feature set size ranges from 256 to 617. For each of them, we executed 12 independent runs in order to obtain statistically stable data. Each run was given 72 hours to observe the long-time convergence. Based on analysis of experimental data, we describe a reason for the superiority and where the scheme can be applied.

• Korean Journal of Human Ecology
• /
• v.18 no.3
• /
• pp.719-727
• /
• 2009

The ultimate success of commercial applications of body scan data in the apparel industry will be consumers' substantial applications such as automated custom fit, size prediction, virtual try-on, personal shopper services (Loker, S. et al., 2004). In this study, we surveyed fifty consumers and forty-seven apparel industry workers about their recognition and interest in 3D body scanning and virtual try-on. The results are as follows: 55% of the apparel industry workers has recognized 3D body scanning as a convenient technology, but do not know how to use it. To the questions regarding virtual try-on, 53% of the workers give positive answers. The consumers have a more positive view on virtual try-on than the workers do. The workers predict that the application of 3D body scan technology to the apparel industry could offer customers helpful information in their clothing selection by using virtual images of various size and style, and increase mass production of MTM(Made-To-Measure). The answers from the male consumers in their twenties indicate that virtual try-on is useful by 88% on offline shopping and by 100% on online shopping. 53% of the workers and 68% of the consumers gave answers that just by virtual try-on they could judge the quality of the apparel products and purchase them. Absolutely 3D virtual try-on is an effective tool for online shoppers. 85% of the workers anticipate applications of the 3D body scanning also in 'body measurement', 'custom pattern development' as well as 'virtual try-on' in the near future. With the positive reactions and the stimulating interests in virtual try-on, the conditions of contemporary world encourage more active researches and wide usages of the technology in apparel industry.

• Journal of Korea Multimedia Society
• /
• v.15 no.7
• /
• pp.870-878
• /
• 2012

Recently, very rapid development of computer and sensor technologies induces various kinds of user interface (UI) technologies based on user experience (UX). In this study, we investigate and develop a smart touch projector system technology on the basis of IR sensor and image processing. In the proposed system, a user can control computer by understanding the control events based on gesture of IR pen as an input device. In the IR image, we extract the movement (or gesture) of the devised pen and track it for recognizing gesture pattern. Also, to correct the error between the coordinate of input image sensor and display device (projector), we propose a coordinate correction algorithm to improve the accuracy of operation. Through this system technology as the next generation human-computer interaction, we can control the events of the equipped computer on the projected image screen without manipulating the computer directly.