• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.55-67
• /
• 1998

This paper presents an automatic facial feature point extraction algorithm in sequential color images. To extract facial region in the video sequence, a moving color detection technique is proposed that emphasize moving skin color region by applying motion detection algorithm on the skin-color transformed images. The threshold value for the pixel difference detection is also decided according to the transformed pixel value that represents the probability of the desired color information. Eye candidate regions are selected using both of the black/white color information inside the skin-color region and the valley information of the moving skin region detected using morphological operators. Eye region is finally decided by the geometrical relationship of the eyes and color histogram. To decide the exact feature points, the PCA(Principal Component Analysis) is used on each eye and mouth regions. Experimental results show that the feature points of eye and mouth can be obtained correctly irrespective of background, direction and size of face.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• Clinics in Shoulder and Elbow
• /
• v.21 no.3
• /
• pp.113-119
• /
• 2018

Background: This study was undertaken to evaluate the positional relationship between planes of the glenoid component (the scapular plane and the perpendicular plane to the glenoid) and its surrounding structures. Methods: Computed tomography (CT) images of both shoulders of 100 patients were evaluated using the 3-dimensional CT reconstruction program ($Aquarius^{(R)}$; TeraRecon). We determined the most lateral scapular bony structure of the scapular plane and measured the shortest distance between the anterolateral corner of the acromion and the scapular plane. The distance between the scapular plane and the midpoint of the line connecting the posterolateral corner of acromion and the anterior tip of the coracoid process (fulcrum axis) was also evaluated. The perpendicular plane was then adjusted to the glenoid and the same values were re-assessed. Results: The acromion was the most lateral scapular structure of scapular plane and perpendicular plane to the glenoid. The average distance from the anterolateral corner of the acromion to the scapular plane was $10.44{\pm}5.11mm$, and to the plane perpendicular to the glenoid was $9.55{\pm}5.13mm$. The midpoint of fulcrum axis was positioned towards the acromion and was measured at $3.90{\pm}3.21mm$ from the scapular plane and at $3.84{\pm}3.17mm$ from the perpendicular plane to the glenoid. Conclusions: Our data indicates that the relationship between the perpendicular plane to the glenoid plane and its surrounding structures is reliable and can be used as guidelines during glenoid component insertion (level of evidence: Level IV, case series, treatment study).

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.3
• /
• pp.303-309
• /
• 2014

The increasing importance of meat quality has implications for animal breeding programs. Research has revealed much about the genetic background of pigs, and many studies have revealed the importance of various genetic factors. Since meat quality is a complex trait which is affected by many factors, consideration of the overall phenotype is very useful to study meat quality. For integrating the phenotypes, we used principle component analysis (PCA). The significant SNPs refer to results of the GRAMMAR method against PC1, PC2 and PC3 of 14 meat quality traits of 181 Duroc pigs. The Genome-wide association study (GWAS) found 26 potential SNPs affecting various meat quality traits. The loci identified are located in or near 23 genes. The SNPs associated with meat quality are in or near five genes (ANK1, BMP6, SHH, PIP4K2A, and FOXN2) and have been reported previously. Twenty-five of the significant SNPs also located in meat quality-related QTL regions, these result supported the QTL effect indirectly. Each single gene typically affects multiple traits. Therefore, it is a useful approach to use integrated traits for the various traits at the same time. This innovative approach using integrated traits could be applied on other GWAS of complex-traits including meat-quality, and the results will contribute to improving meat-quality of pork.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.10
• /
• pp.4199-4202
• /
• 2015

Background: Hepatitis B virus infection is one of the major world health problems. Epigallocatechin-3 gallate is the major component of the polyphenolic fraction of green tea and it has an anti-viral, anti-mutagenic, anti-tumorigenic, anti-angiogenic, anti-proliferative, and/or pro-apoptotic effects on mammalian cells. In this study, our aim was to investigate the inhibition of HBV replication by epigallocatechin-3 gallate in the Hep3B2.1-7 hepatocellular carcinoma cell line. Materials and Methods: HBV-replicating Hep3B2.1-7 cells were used to investigate the preventive effects of epigallocatechin-3 gallate on HBV DNA replication. The expression levels of HBsAg and HBeAg were determined using ELISA. Quantitative real-time-PCR was applied for the determination of the expression level of HBV DNA. Results: Cytotoxicity of epigallocathechin-3-gallate was not observed in the hepatic carcinoma cell line when the dose was lower than $100{\mu}M$. The ELISA method demonstrated that epigallocatechin-3 gallate have strong effects on HBsAg and HBeAg levels. Also it was detected by real-time PCR that epigallocatechin-3 gallate could prevent HBV DNA replication. Conclusions: The obtained data pointed out that although the exact mechanism of HBV DNA replication and related diseases remains unclear, epigallocatechin-3 gallate has a potential as an effective anti-HBV agent with low toxicity.

• Journal of Korea Multimedia Society
• /
• v.7 no.7
• /
• pp.877-885
• /
• 2004

In this paper, we propose an enhancement shot change detection method using the neural net and the robust feature selection out of multiple features. The previous shot change detection methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using robust features, which are supplementary each other, rather than using single feature. In this paper, we use the typical CART (classification and regression tree) of data mining method to select the robust features, and the backpropagation neural net to determine the threshold of the each selected features. And to evaluation the performance of the robust feature selection, we compare the proposed method to the PCA(principal component analysis) method of the typical feature selection. According to the experimental result. it was revealed that the performance of our method had better that than the PCA method.

• Journal of Advanced Navigation Technology
• /
• v.15 no.4
• /
• pp.672-679
• /
• 2011

In this paper, detection algorithm of face region based on skin color of in the TV images is proposed. In the first, reference image is set to the sampled skin color, and then the extracted of face region is candidated using the Euclidean distance between the pixels of TV image. The eye image is detected by using the mean value and standard deviation of the component forming color difference between Y and C through the conversion of RGB color into CMY color model. Detecting the lips image is calculated by utilizing Q component through the conversion of RGB color model into YIQ color space. The detection of the face region is extracted using basis of knowledge by doing logical calculation of the eye image and lips image. To testify the proposed method, some experiments are performed using front color image down loaded from TV color image. Experimental results showed that face region can be detected in both case of the irrespective location & size of the human face.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.31-40
• /
• 2006

In this paper, we propose a gait recognition method based on gait silhouette sequences. Features of gait are affected by the variation of gait direction. Therefore, we synthesize silhouettes to canonical form by using planar homography in order to reduce the effect of the variation of gait direction. The planar homography is estimated with only the information which exist within the gait sequences without complicate operations such as camera calibration. Even though gait silhouettes are generated from an individual person, fragments beyond common characteristics exist because of errors caused by inaccuracy of background subtraction algorithm. In this paper, we use the Principal Component Analysis to analyze the deviated characteristics of each individual person. PCA used in this paper, however, is not same as the traditional strategy used in pattern classification. We use PCA as a criterion to analyze the amount of deviation from common characteristic. Experimental results show that the proposed method is robust to the variation of gait direction and improves separability of test-data groups.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.77-85
• /
• 2006

In this paper, we propose a hierarchical classifier of object images using neural networks for content-based image classification. The images for classification are object images that can be divided into foreground and background. In the preprocessing step, we extract the object region and shape-based texture features extracted from wavelet transformed images. We group the image classes into clusters which have similar texture features using Principal Component Analysis(PCA) and K-means. The hierarchical classifier has five layes which combine the clusters. The hierarchical classifier consists of 59 neural network classifiers learned with the back propagation algorithm. Among the various texture features, the diagonal moment was the most effective. A test with 1000 training data and 1000 test data composed of 10 images from each of 100 classes shows classification rates of 81.5% and 75.1% correct, respectively.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.451-463
• /
• 2007

This paper describes issues of GPS network adjustment to determine coordinate sets of the $2^{nd}$ order national geodetic control points based on the Korean Geodetic Datum (KGD2002) which has been newly adopted in 2003, After outlining theoretical background of the GPS network processing, the adjustment procedure applied for this project is detailed. Throughout performing a series of minimally constrained adjustments, some outliers have been removed and magnitude of absolute and relative error for a stochastic modeling has been determined as 4mm+0.4ppm and 8mm+0.8ppm in the horizontal and vertical component, respectively. The over constrained adjustment by fixing the $1^{st}$ order control points was performed to derive final solution, indicating that the accuracy of the estimated coordinates was 2cm and 4cm in the horizontal and vertical component.