• Title/Summary/Keyword: NA matching

Search Result 85, Processing Time 0.031 seconds

Performance Evaluation of Multimodal Biometric System for Normalization Methods and Classifiers (균등화 및 분류기에 따른 다중 생체 인식 시스템의 성능 평가)

  • Go, Hyoun-Ju;Woo, Na-Young;Shin, Yong-Nyuo;Kim, Jae-Sung;Kim, Hak-Il;Chun, Myung-Geun
    • Journal of KIISE:Software and Applications
    • /
    • v.34 no.4
    • /
    • pp.377-388
    • /
    • 2007
  • In this paper, we propose a multi-modal biometric system based on face, iris and fingerprint recognition system. To effectively aggregate two systems, we use statistical distribution models based on matching values for genuine and impostor, respectively. And then, We performed reveal fusion algorithms including weighted summation, Support Vector Machine(SVM), Fisher discriminant analysis, Bayesian classifier. From the various experiments, we found that the performance of multi-modal biometric system was influenced with the normalization methods and classifiers.

Virtual DressUp system by using image deformation method (이미지 변형 기법을 이용한 가상 드레스업 시스템)

  • Kim, Na-Ri;Yoon, Jong-Chul;Lee, In-Kwon
    • Journal of the Korea Computer Graphics Society
    • /
    • v.15 no.2
    • /
    • pp.1-8
    • /
    • 2009
  • This paper introduces a virtual dress up system, according to user's input model and garment image. At first step, we deform the garment image by using skeleton structures and ARAP method. Next step, sampling the boundary points and find their matching vertices which are used for optimizing the boundary fitting. In 2D rendering of the dress up, they have some unrealistic results, so we reconstruct the garment mesh to the 3D mesh. Rendering from the reconstructed 3D mesh, we can get the final dress up result. We present that our system produce a visually plausible and well-fitted virtual dress up results.

  • PDF

Parallel Computation for Extended Edit Distances Using the Shared Memory on GPU (GPU의 공유메모리를 활용한 확장편집거리 병렬계산)

  • Kim, Youngho;Na, Joong Chae;Sim, Jeong Seop
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.4 no.7
    • /
    • pp.213-218
    • /
    • 2015
  • Given two strings X and Y (|X|=m, |Y|=n) over an alphabet ${\Sigma}$, the extended edit distance between X and Y can be computed using dynamic programming in O(mn) time and space. Recently, a parallel algorithm that takes O(m+n) time and O(mn) space using m threads to compute the extended edit distance between X and Y was presented. In this paper, we present an improved parallel algorithm using the shared memory on GPU. The experimental results show that our parallel algorithm runs about 19~25 times faster than the previous parallel algorithm.

The Oosterhoff period groups and multiple populations in globular clusters

  • Jang, Sohee;Lee, Young-Wook;Joo, Seok-Joo;Na, Chongsam
    • The Bulletin of The Korean Astronomical Society
    • /
    • v.39 no.1
    • /
    • pp.82.1-82.1
    • /
    • 2014
  • The presence of multiple populations is now well-established in most globular clusters (GCs) in the Milky Way. In light of this progress, here we suggest a new model explaining the origin of the Sandage period-shift and the difference in mean period of type ab RR Lyrae variables () between the two Oosterhoff groups. In our models, while matching the observed color-magnitude diagrams, the difference in is naturally reproduced as the instability strip is occupied by different subpopulations with increasing metallicity. The instability strip in the metal-poor group II clusters is populated by second generation stars (G2) with enhanced helium and CNO abundances, while the RR Lyraes in the metal-rich group I clusters are mostly produced by first generation stars (G1) without these enhancements. This population shift within the instability strip can create the observed period-shift between the two groups, since both helium and CNO abundances play a role in increasing the period of RR Lyrae variables. The presence of more metal-rich Oosterhoff group III clusters having RR Lyraes with longest can also be reproduced, if more helium-rich third generation stars (G3) are present in these GCs.

  • PDF

Thick Film Type duster in Mg2SiO4/Glass composite ceramics for Anion Generation (Mg2SiO4/Glass Composite계 세라믹스를 이용한 음이온 발생용 후막형 클러스터)

  • Yeo, Dong-Hun;Shin, Hyo-Soon;Hong, Youn-Woo
    • Journal of the Korean Institute of Electrical and Electronic Material Engineers
    • /
    • v.23 no.2
    • /
    • pp.118-123
    • /
    • 2010
  • The eco-friendly technologies have been extended as matter of international concern due to various diseases and syndromes according to an environmental pollution. In this study, we have manufactured a ceramic cluster with thick film type for anion generation equipment which is maximized anion but minimized ozone contents generated. To develop the formulation of ceramic cluster, we conducted the $Mg_2SiO_4$ powders doped with 10 vol% glass frits as Na-Zn-B-O system and sintered at $1050^{\circ}C$ for 2 hours in air for starting materials and investigated the matching properties between the Ag-Pd electrode and the starting materials. The sintered sample for the composition of cluster has 6.7 of dielectric constant and 32 kV/mm of withstand voltage. The yield of anions was measured according to an electrode pattering, discharge gap between electrode, and thickness of electrode protective layer in the cluster of thick film type. We have manufactured the ceramic clusters with optimized thick film structure that have an anion over a hundred particles and the ozone of 0.6 ppb generated.

A Study on Drowsy Driving Detection using SURF (SURF를 이용한 졸음운전 검출에 관한 연구)

  • Choi, Na-Ri;Choi, Ki-Ho
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.11 no.4
    • /
    • pp.131-143
    • /
    • 2012
  • In this paper, we propose a drowsy driver detection system with a novel eye state detection method that is adaptive to various vehicle environment such as glasses, light and so forth using SURF(Speed Up Robust Feature) which can extract quickly local features from images. Also the performance of eye state detection is improved as individual three eye-state templates of each driver can be made using Bayesian inference. The experimental results under various environment with average 98.1% and 96.1% detection rate in the daytime and at night respectively and those in the opened ZJU database with average 97.8% detection rate show that the proposed method outperforms the current state-of-the-art.

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

  • Ma, Na;Wen, Tingxin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.15 no.6
    • /
    • pp.2098-2114
    • /
    • 2021
  • Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

Wavelet Transform-based Face Detection for Real-time Applications (실시간 응용을 위한 웨이블릿 변환 기반의 얼굴 검출)

  • 송해진;고병철;변혜란
    • Journal of KIISE:Software and Applications
    • /
    • v.30 no.9
    • /
    • pp.829-842
    • /
    • 2003
  • In this Paper, we propose the new face detection and tracking method based on template matching for real-time applications such as, teleconference, telecommunication, front stage of surveillance system using face recognition, and video-phone applications. Since the main purpose of paper is to track a face regardless of various environments, we use template-based face tracking method. To generate robust face templates, we apply wavelet transform to the average face image and extract three types of wavelet template from transformed low-resolution average face. However template matching is generally sensitive to the change of illumination conditions, we apply Min-max normalization with histogram equalization according to the variation of intensity. Tracking method is also applied to reduce the computation time and predict precise face candidate region. Finally, facial components are also detected and from the relative distance of two eyes, we estimate the size of facial ellipse.

Container BIC-code region extraction and recognition method using multiple thresholding (다중 이진화를 이용한 컨테이너 BIC 부호 영역 추출 및 인식 방법)

  • Song, Jae-wook;Jung, Na-ra;Kang, Hyun-soo
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.19 no.6
    • /
    • pp.1462-1470
    • /
    • 2015
  • The container BIC-code is a transport protocol for convenience in international shipping and combined transport environment. It is an identification code of a marine transport container which displays a wide variety of information including country's code. Recently, transportation through aircrafts and ships continues to rise. Thus fast and accurate processes are required in the ports to manage transportation. Accordingly, in this paper, we propose a BIC-code region extraction and recognition method using multiple thresholds. In the code recognition, applying a fixed threshold is not reasonable due to a variety of illumination conditions caused by change of weather, lightening, camera position, color of the container and so on. Thus, the proposed method selects the best recognition result at the final stage after applying multiple thresholds to recognition. For each threshold, we performs binarization, labeling, BIC-code pattern decision (horizontal or vertical pattern) by morphological close operation, and character separation from the BIC-code. Then, each characters is recognized by template matching. Finally we measure recognition confidence scores for all the thresholds and choose the best one. Experimental results show that the proposed method yields accurate recognition for the container BIC-code with robustness to illumination change.

Multifilament Cable Wire versus Conventional Wire for Sternal Closure in Patients Undergoing Major Cardiac Surgery

  • Oh, You Na;Ha, Keong Jun;Kim, Joon Bum;Jung, Sung-Ho;Choo, Suk Jung;Chung, Cheol Hyun;Lee, Jae Won
    • Journal of Chest Surgery
    • /
    • v.48 no.4
    • /
    • pp.265-271
    • /
    • 2015
  • Background: Stainless steel wiring remains the most popular technique for primary sternal closure. Recently, a multifilament cable wiring system (Pioneer Surgical Technology Inc., Marquette, MI, USA) was introduced for sternal closure and has gained wide acceptance due to its superior resistance to tension. We aimed to compare conventional steel wiring to multifilament cable fixation for sternal closure in patients undergoing major cardiac surgery. Methods: Data were collected retrospectively on 1,354 patients who underwent sternal closure after major cardiac surgery, using either the multifilament cable wiring system or conventional steel wires between January 2009 and October 2010. The surgical outcomes of these two groups of patients were compared using propensity score matching based on 18 baseline patient characteristics. Results: Propensity score matching yielded 392 pairs of patients in the two groups whose baseline profiles showed no significant differences. No significant differences between the two groups were observed in the rates of early mortality (2.0% vs. 1.3%, p=0.578), major wound complications requiring reconstruction (1.3% vs. 1.3%, p>0.99), minor wound complications (3.6% vs. 2.0%, p=0.279), or mediastinitis (0.8% vs. 1.0%, p=1.00). Patients in the multifilament cable group had fewer sternal bleeding events than those in the conventional wire group, but this tendency was not statistically significant (4.3% vs. 7.4%, p=0.068). Conclusion: The surgical outcomes of sternal closure using multifilament cable wires were comparable to those observed when conventional steel wires were used. Therefore, the multifilament cable wiring system may be considered a viable option for sternal closure in patients undergoing major cardiac surgery.