• Title/Summary/Keyword: Affine invariant

Search Result 61, Processing Time 0.024 seconds

Affine Invariant Local Descriptors for Face Recognition (얼굴인식을 위한 어파인 불변 지역 서술자)

  • Gao, Yongbin;Lee, Hyo Jong
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.3 no.9
    • /
    • pp.375-380
    • /
    • 2014
  • Under controlled environment, such as fixed viewpoints or consistent illumination, the performance of face recognition is usually high enough to be acceptable nowadays. Face recognition is, however, a still challenging task in real world. SIFT(Scale Invariant Feature Transformation) algorithm is scale and rotation invariant, which is powerful only in the case of small viewpoint changes. However, it often fails when viewpoint of faces changes in wide range. In this paper, we use Affine SIFT (Scale Invariant Feature Transformation; ASIFT) to detect affine invariant local descriptors for face recognition under wide viewpoint changes. The ASIFT is an extension of SIFT algorithm to solve this weakness. In our scheme, ASIFT is applied only to gallery face, while SIFT algorithm is applied to probe face. ASIFT generates a series of different viewpoints using affine transformation. Therefore, the ASIFT allows viewpoint differences between gallery face and probe face. Experiment results showed our framework achieved higher recognition accuracy than the original SIFT algorithm on FERET database.

INVARIANT OPEN SETS UNDER COCOMPACT AFFINE ACTIONS

  • Park, Kyeong-Su
    • Bulletin of the Korean Mathematical Society
    • /
    • v.36 no.1
    • /
    • pp.203-207
    • /
    • 1999
  • In this paper, we find a condition of an open subset of the affine space which admits a cocompact affine action. To do it, the asymptotic flag of an open convex subset is introduced and some applications to affine manifolds are presented.

  • PDF

Affine-Invariant Image normalization for Log-Polar Images using Momentums

  • Son, Young-Ho;You, Bum-Jae;Oh, Sang-Rok;Park, Gwi-Tae
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.1140-1145
    • /
    • 2003
  • Image normalization is one of the important areas in pattern recognition. Also, log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. We propose an image normalization technique of log-polar images using momentums applicable for affine-invariant pattern recognition. We handle basic distortions of an image including translation, rotation, scaling, and skew of a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.

  • PDF

ENLARGING THE BALL OF CONVERGENCE OF SECANT-LIKE METHODS FOR NON-DIFFERENTIABLE OPERATORS

  • Argyros, Ioannis K.;Ren, Hongmin
    • Journal of the Korean Mathematical Society
    • /
    • v.55 no.1
    • /
    • pp.17-28
    • /
    • 2018
  • In this paper, we enlarge the ball of convergence of a uniparametric family of secant-like methods for solving non-differentiable operators equations in Banach spaces via using ${\omega}$-condition and centered-like ${\omega}$-condition meantime as well as some fine techniques such as the affine invariant form. Numerical examples are also provided.

A MODIFIED INEXACT NEWTON METHOD

  • Huang, Pengzhan;Abduwali, Abdurishit
    • Journal of applied mathematics & informatics
    • /
    • v.33 no.1_2
    • /
    • pp.127-143
    • /
    • 2015
  • In this paper, we consider a modified inexact Newton method for solving a nonlinear system F(x) = 0 where $F(x):R^n{\rightarrow}R^n$. The basic idea is to accelerate convergence. A semi-local convergence theorem for the modified inexact Newton method is established and an affine invariant version is also given. Moreover, we test three numerical examples which show that the modified inexact scheme is more efficient than the classical inexact Newton strategy.

Invariant Detection of Periodic Motion using Affine Model (Periodic Motion의 Invariant Detection을 위한 Affine Model 적용)

  • Choi, Woo-Jin;Chung, Chin-Hyun
    • Proceedings of the KIEE Conference
    • /
    • 1998.07g
    • /
    • pp.2237-2239
    • /
    • 1998
  • A limitation is assumed that In this paper, a generalized method is proposed to extract a period of a motion of on object. To detect a periodic motion, we put restrictions on a stationary camera and on a motion of an object. We ca derive the necessary and sufficient condition that an image sequence consists of the projection of the periodic motion by the affine transformation that is a reasonally good approach to the perspective projection. The difficulty of detecting its periodic motion is to select its have period in sequence and to define its width.

  • PDF

AFFINE INNER AUTOMORPHISMS BETWEEN COMPACT CONNECTED SEMISIMPLE LIE GROUPS

  • Park, Joon-Sik
    • Journal of applied mathematics & informatics
    • /
    • v.9 no.2
    • /
    • pp.859-867
    • /
    • 2002
  • In this paper, we get a necessary and sufficient condition for an inner automorphism between compact connected semisimple Lie groups to be an atone transformation, and obtain atone transformations of (SU(n),g) with some left invariant metric g.

AFFINE INVARIANT LOCAL CONVERGENCE THEOREMS FOR INEXACT NEWTON-LIKE METHODS

  • Argyros, Ioannis K.
    • Journal of applied mathematics & informatics
    • /
    • v.6 no.2
    • /
    • pp.393-406
    • /
    • 1999
  • Affine invariant sufficient conditions are given for two local convergence theorems involving inexact Newton-like methods. The first uses conditions on the first Frechet-derivative whereas the second theorem employs hypotheses on the second. Radius of con-vergence as well as rate of convergence results are derived. Results involving superlinear convergence and known to be true for inexact Newton methods are extended here. Moreover we show that under hypotheses on the second Frechet-derivation our radius of convergence results are derived. Results involving superlinear convergence and known to be true or inexact Newton methods are extended here. Moreover we show that under hypotheses on the second Frechet-derivative our radius of conver-gence is larger than the corresponding one in [10]. This allows a wider choice for the initial guess. A numerical example is also pro-vided to show that our radius of convergence is larger then the one in [10].

IMPROVING THE ORDER AND RATES OF CONVERGENCE FOR THE SUPER-HALLEY METHOD IN BANACH SPACES

  • Argyros, Ioannis-K.
    • Journal of applied mathematics & informatics
    • /
    • v.5 no.2
    • /
    • pp.507-516
    • /
    • 1998
  • In this study we are concerned with the problem of ap-proximating a locally unique solution of an equation on a Banach space. A semilocal convergence theorem is given for the Super-Halley method in Banach spaces. Earlier results have shown that the order of convergence is four for a certain class of operators [4] [5] [8] These results were not given in affine invariant form and made use of a real quadratic majorizing polynomial. Here we provide our re-sults in affine invariant form showing that the order of convergence is at least four. In cases that it is exactly four the rate of convergence is improved. We achieve these results by using a cubic majorizing polynomial. Some numerical examples are given to show that our error bounds are better than earlier ones.