• Title/Summary/Keyword: Similarity Transformation

Search Result 163, Processing Time 0.034 seconds

Wavelet-Based Face Recognition by Divided Area (웨이브렛을 이용한 공간적 영역분할에 의한 얼굴 인식)

  • 이성록;이상효;조창호;조도현;이상철
    • Proceedings of the IEEK Conference
    • /
    • 2003.07e
    • /
    • pp.2307-2310
    • /
    • 2003
  • In this paper, a method for face recognition based on the wavelet packet decomposition is proposed. In the proposed method, the input image is decomposed by the 2-level wavelet packet transformation and then the face areas are defined by the Integral Projection technique applied to each of the 1-level subband images, HL and LH. After the defined face areas are divided into three areas, called top, bottom, and border, the mean and the variance of the three areas of the approximation image are computed, and the variance of the single predetermined face area for the rest of 15 detail images, from which the feature vectors of statistical measure are extracted. In this paper we use the wavelet packet decomposition, a generalization of the classical wavelet decomposition, to obtain its richer signal analysis features such as discontinuity in higher derivatives, self-similarity, etc. And we have shown that even with very simple statistical features such as mean values and variance we can make an excellent basis for face classification, if an appropriate probability distance is used.

  • PDF

GENERALIZED EULER PROCESS FOR SYSTEMS OF NONLINEAR DIFFERENTIAL EQUATIONS

  • Yu, Dong-Won
    • Journal of applied mathematics & informatics
    • /
    • v.7 no.3
    • /
    • pp.941-958
    • /
    • 2000
  • Euler method is generalized to solve the system of nonlinear differential equations. The generalization is carried out by taking a special constant matrix S so that exp(tS) can be exactly computed. Such a matrix S is extracted from the Jacobian matrix of the given problem. Stability of the generalized Euler process is discussed. It is shown that the generalized Euler process is comparable to the fourth order Runge-Kutta method. We also exemplify that the important qualitative and geometric features of the underlying dynamical system can be recovered by the generalized Euler process.

An Effective Sequence for Robust Watermarking in Wavelet Domain (웨이브릿 영역에서 강인한 워터마킹을 위한 효율적인 시퀀스)

  • 송상주;박두순
    • Journal of Korea Multimedia Society
    • /
    • v.4 no.6
    • /
    • pp.554-561
    • /
    • 2001
  • Wavelet transformation method which has special qualities of frequency domain and spatial domain is used for watermarking. We have compared the decree of similarity to find a robust watermarking sequence for different attacks, using random number, gaussian sequence, chaos sequence and sobel sequence. The experimental results show that chaos sequence is an effective sequence for robust watermarking.

  • PDF

A View on the Validity of Central Limit Theorem: An Empirical Study Using Random Samples from Uniform Distribution

  • Lee, Chanmi;Kim, Seungah;Jeong, Jaesik
    • Communications for Statistical Applications and Methods
    • /
    • v.21 no.6
    • /
    • pp.539-559
    • /
    • 2014
  • We derive the exact distribution of summation for random samples from uniform distribution and then compare the exact distribution with the approximated normal distribution obtained by the central limit theorem. To check the similarity between two distributions, we consider five existing normality tests based on the difference between the target normal distribution and empirical distribution: Anderson-Darling test, Kolmogorov-Smirnov test, Cramer-von Mises test, Shapiro-Wilk test and Shaprio-Francia test. For the purpose of comparison, those normality tests are applied to the simulated data. It can sometimes be difficult to derive an exact distribution. Thus, we try two different transformations to find out which transform is easier to get the exact distribution in terms of calculation complexity. We compare two transformations and comment on the advantages and disadvantages for each transformation.

The Hydrodynamic Stability of Natural Convection Flows Adjacent to an Inclined Isothermal Surface Submerged in Cold, Pure Water (순수한 찬물속에 잠겨있는 경사진 등온벽면 부근의 자연대류에 관한 수동력학적 안정성)

  • Hwang, Y.K.;Jang, M.R.
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.2 no.4
    • /
    • pp.268-278
    • /
    • 1990
  • Hydrodynamic stability equations are formulated for natural convection flows adjacent to a heated or cooled, inclined, isothermal surface in pure water at $4^{\circ}C$, where the density variation with temperature becomes nonlinear. The resulting stability equations, when reduced to ordinary differential equations by a similarity transformation, constitute a two-point boundary-value problem, which was solved numerically. It is found from the obtained stability results that the neutral stability curves are systematically shifted to have lower critical Grashof numbers, as the inclination angle of upward-facing plate increases. Also, the nose of the neutral stability curve becomes blunter as the angle increases. It implies that the greater the inclination of the upward-facing plate, the more susceptible of the flow to instability for the wide range of disturbance wave number and frequency.

  • PDF

An Adaptive Steganography of Optical Image using Bit-Planes and Multi-channel Characteristics

  • Kang, Jin-Suk;Jeong, Taik-Yeong T.
    • Journal of the Optical Society of Korea
    • /
    • v.12 no.3
    • /
    • pp.136-146
    • /
    • 2008
  • We proposed an adaptive steganography of an optical image using bit-planes and multichannel characteristics. The experiment's purpose was to compare the most popular methods used in optical steganography and to examine their advantages and disadvantages. In this paper we describe two digital methods: the first uses less significant bits(LSB) to encode hidden data, and in the other all blocks of $n{\times}n$ pixels are coded by using DCT(Digital Cosine Transformation), and two optical methods: double phase encoding and digital hologram watermarking with double binary phase encoding by using IFTA(Iterative Fourier Transform Algorithm) with phase quantization. Therefore, we investigated the complexity on bit plane and data, similarity insert information into bit planes. As a result, the proposed method increased the insertion capacity and improved the optical image quality as compared to fixing threshold and variable length method.

Non Darcy Mixed Convection Flow of Magnetic Fluid over a Permeable Stretching Sheet with Ohmic Dissipation

  • Zeeshan, A.;Majeed, A.
    • Journal of Magnetics
    • /
    • v.21 no.1
    • /
    • pp.153-158
    • /
    • 2016
  • This paper aims to discuss the Non Darcy boundary layer flow of non-conducting viscous fluid with magnetic ferroparticles over a permeable linearly stretching surface with ohmic dissipation and mixed convective heat transfer. A magnetic dipole is applied "a" distance below the surface of stretching sheet. The governing equations are modeled. Similarity transformation is used to convert the system of partial differential equations to a system of non-linear but ordinary differential equations. The ODEs are solved numerically. The effects of sundry parameters on the flow properties like velocity, pressure, skin-friction coefficient and Nusselt number are presented. It is deduced the frictional resistance of Lorentz force decreases with stronger electric field and the trend reverses for temperature. Skin friction coefficient increase with increase in ferromagnetic interaction parameter. Whereas, Nusselt number decrease.

Characteristics of Partially Premixed Flames in Double Concentric Burner (이중 동축류 버너에서 부분예혼합화염의 특성에 관한 연구)

  • Kwon, S.J.;Cha, M.S.;Chung, S.H.
    • 한국연소학회:학술대회논문집
    • /
    • 1998.10a
    • /
    • pp.131-138
    • /
    • 1998
  • Flame characteristics in a double concentric burner has been studied experimentally. Air is supplied through a central nozzle, methane/air premixture is supplied in a inner annular part, and coflowing shield air is supplied to minimize outside disturbances. Depending on flow rate and concentration, various flame shapes can be observed. As the flow rate difference between central air jet and annular premixed jet is varied, several distinctive flames are observed. Conditions of partially premixed flames are further investigated; nozzle attached rich premixed flame, inner lifted flame, and outer lifted flame. Using the Abel transformation of digitized images of flames, cross- sectional images of flames can be obtained, from which overall structure of flames can be identified. PLIF measurement of OR radical was also conducted. OR radicals were mainly distributed in diffusion flame region. From the difference of OR distribution between nozzle attached and lifted flames, similarity of OR distribution between tribrachial flame and lifted flames in this study are observed.

  • PDF

증발을 고려한 Wafer Spin Coating 박막 예측에 관한 수치 해석적 연구

  • 노영미;임익태;김광선
    • Proceedings of the Korean Society Of Semiconductor Equipment Technology
    • /
    • 2002.11a
    • /
    • pp.20-26
    • /
    • 2002
  • The fluid flow, mass transfer, heat transfer and film thickness variation during the spin coating process are numerically studied. The model is said to be 1-dimensional because radial variations in film thickness, concentration and temperature are ignored. The finite difference method is employed to solve the equations that are simplified using the similarity transformation. In early time film thinning is due to the radial convective outflow. However that slows during the first seconds of spinning so the film thinning due to evaporation of solvent becomes sole. The time various film thickness is analyzed according to the var ious solvent fraction in the coating liquid and in the bulk of the overlying gas and the temperature variation in the liquid film during the spin coating is estimated.

  • PDF

Object Classification Method using Hilbert Scanning Distance (힐버트 스캔 거리값을 이용한 물체식별 알고리즘)

  • Choi, Jeong-Hwan;Baek, Young-Min;Choi, Jin-Young
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.57 no.4
    • /
    • pp.700-705
    • /
    • 2008
  • In this paper, we propose object classification algorithm for real-time surveillance system. We have approached this problem using silhouette-based template matching. The silhouette of the object is extracted, and then it is compared with representative template models. Template models are previously stored in the database. Our algorithm is similar to previous pixel-based template matching scheme like Hausdorff Distance, but we use 1D image array rather than 2D regions inspired by Hilbert Path. Transformation of images could reduce computational burden to compute similarity between the detected image and the template images. Experimental results show robustness and real-time performance in object classification, even in low resolution images.