• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.

• The Journal of Society for e-Business Studies
• /
• v.20 no.4
• /
• pp.61-76
• /
• 2015

In general, we have utilized the hierarchical concept tree as a crucial data structure for indexing huge amount of textual data. This paper proposes a generality rank-based method that can automatically develop hierarchical concept structures with the Wikipedia data. The goal of the method is to regard each of Wikipedia articles as a concept and to generate hierarchical relationships among concepts. In order to estimate the generality of concepts, we have devised a special ranking function that mainly uses the number of hyperlinks among Wikipedia articles. The ranking function is effectively used for computing the probabilistic subsumption among concepts, which allows to generate relatively more stable hierarchical structures. Eventually, a set of concept pairs with hierarchical relationship is visualized as a DAG (directed acyclic graph). Through the empirical analysis using the concept hierarchy of Open Directory Project, we proved that the proposed method outperforms a representative baseline method and it can automatically extract concept hierarchies with high accuracy.

• Korean Journal of Microbiology
• /
• v.34 no.1_2
• /
• pp.58-63
• /
• 1998

Fragment assembly problem is to reconstruct DNA sequence contigs from a collection of fragment sequences. We have developed an efficient X-window program, XFAP, for assembling DNA fragments. In the XFAP, the dimer frequency comparison method is used to quickly eliminate pairs of fragments that can not overlap. This method takes advantage of the difference of dimer frequencies within the minimum acceptable overlap length in each fragment pair. Hirschberg algorithm is applied to compute the maximal-scoring overlapping alignment in linear space. The perfomance of XFAP was tested on a set of DNA fragment sequences extracted from long DNA sequences of GenBank by a fragmentation program and showed a great improvement in execution time, especially as the number of fragments increases.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.1
• /
• pp.14-22
• /
• 2009

By calculating the differences between two images, which are captured with the same scene at different time, we can detect a set of outliers, such as occluding objects due to moving vehicles. To reduce the influence from the different intensity properties of the images, a simple technique that reruns the regression, which is based on the polynomial regression model, is employed. For a robust detection of outliers, the image difference is normalized by the noise variance. Hence, an accurate estimate of the noise variance is very important. In this paper, using an empirically obtained correction constant is proposed. Numerical analysis using both synthetic and real images are also shown in this paper to show the robust performance of the detection algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.2
• /
• pp.163-171
• /
• 1997

Function approximation from a set of input-output pairs has numerous applications in scientific and engineering areas. Multilayer feedforward neural networks have been proposed as a good approximator of nonlinear function. The back propagation(BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. It iteratively adjusts the network parameters(weights) to minimize the sum of squared approximation errors using a gradient descent technique. However, the mapping acquired through the BP algorithm may be corrupt when errorneous training data we employed. When errorneous traning data are employed, the learned mapping can oscillate badly between data points. In this paper we propose a robust BP learning algorithm that is resistant to the errorneous data and is capable of rejecting gross errors during the approximation process, that is stable under small noise perturbation and robust against gross errors.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.1
• /
• pp.667-675
• /
• 2009

Image matching is widely applied in image application areas, such as remote sensing and GIS. In general, the initial set of matching points always includes outlier which affect the accuracy of image matching. The purpose of this paper is to develop a robust approach for outlier detection and removal in order to keep accuracy in image matching applications. In this paper we use three automatic outlier detection techniques of backward matching and affine transformation, and RANSAC(RANdom SAmple Consensus) algorithm. Moreover, we calculate overlapping apply and steps block-based processing for fast and efficient image matching in pre-processing steps. The suggested approach in this paper has been applied to real frame image pairs and the results have been analyzed in terms of the robustness and the efficiency.

• Journal of Microbiology
• /
• v.37 no.3
• /
• pp.168-174
• /
• 1999

Escherichia coli O157 is an important pathogenic organism which causes diarrhea, haemorrhagic colitis, and haemolytic ureamic syndrome (HUS) in human. E. coli O157 KNIH317 was isolated form patients suffering with HUS in Korea. We designed a primer set for cloning shiga-like toxin (slt) gene. The amplified PCR product was used to Southern and colony hybridization as a probe. As a result, we cloned 4.5-kb KpnI fragment containing the slt gene encoding shiga-like toxin from chromosomal DNA of E. coli O157 KNIH317. This recombinant plasmid was named pOVT45. E. coli XL1-Blue harboring pOVT45 showed cytotoxicity in Vero cells. We sequenced the slt gene of this strain. The A-subunit gene of the slt was composed of 960 base pairs with ATG initiation codon and TAA terminationcodon. The B-subunit was composed of 270 base paris with ATG initiation codon and TGA termination codon. Nucleotide sequence comparison of the slt gene exhibited 100%, 98.4%, 93.7%, and 93.7% identity with that of shiga-like toxin type II (sltII) of E. coli bacteriophage 933W, variant slt of E. coli, slt of E. coli, and variant sltII of E. coli, respectively. From these results, it was concluded that the cloned slt gene belongs to SltII family and that the strain used in this study may be a lysogeny of E. coli bcteriphage 933W.

• Journal of Life Science
• /
• v.21 no.5
• /
• pp.626-630
• /
• 2011

In October 2008, a pair of Crested ibis Nipponia nippon, an endangered avian species in the world, was donated to Korea from China. They have since been the subject of a successful program to incubate chicks for the first time in South Korea. This study was carried out to determine the sex of chicks from the Crested ibis through polymerase chain reaction (PCR) using the sex-related gene and the chromodomain helicase DNA binding protein (CHD) gene. The result of the CHD gene, which was used with a single set of primers and a restriction enzyme treatment after the PCR process, was more accurate in identifying the gender of the Crested ibis. In addition, we compared the CHD gene sequences with the previously reported sequences and found 1~2 different bases between females (CI2, CI4, CI5, and CI6) than in studies previously reporting female sequences.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1478-1484
• /
• 2004

This paper presents a method that controls facial expression in realtime of 3D avatar by having the user select a sequence of facial expressions in the space of facial expressions. The space of expression is created from about 2400 frames of facial expressions. To represent the state of each expression, we use the distance matrix that represents the distances between pairs of feature points on the face. The set of distance matrices is used as the space of expressions. Facial expression of 3D avatar is controled in real time as the user navigates the space. To help this process, we visualized the space of expressions in 2D space by using the Principal Component Analysis(PCA) projection. To see how effective this system is, we had users control facial expressions of 3D avatar by using the system. This paper evaluates the results.

• The KIPS Transactions:PartA
• /
• v.14A no.7
• /
• pp.435-442
• /
• 2007

This paper is concerned with the mesh segmentation problem that can be applied to diverse applications such as texture mapping, simplification, morphing, compression, and shape matching for 3D mesh models. The mesh segmentation is the process of dividing a given mesh into the disjoint set of sub-meshes. We propose a method for segmenting meshes by simultaneously reflecting global and local geometric characteristics of the meshes. First, we extract sharp vertices over mesh vertices by interpreting the curvatures and convexity of a given mesh, which are respectively contained in the local and global geometric characteristics of the mesh. Next, we partition the sharp vertices into the $\kappa$ number of clusters by adopting the $\kappa$-means clustering method [29] based on the Euclidean distances between all pairs of the sharp vertices. Other vertices excluding the sharp vertices are merged into the nearest clusters by Euclidean distances. Also we implement the proposed method and visualize its experimental results on several 3D mesh models.