• Annual Conference of KIPS
• /
• 2014.04a
• /
• pp.781-784
• /
• 2014

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we use Affine SIFT to detect affine invariant local descriptors for face recognition under large viewpoint change. Affine SIFT is an extension of SIFT algorithm. SIFT algorithm is scale and rotation invariant, which is powerful for small viewpoint changes in face recognition, but it fails when large viewpoint change exists. In our scheme, Affine SIFT is used for both gallery face and probe face, which generates a series of different viewpoints using affine transformation. Therefore, Affine SIFT allows viewpoint difference between gallery face and probe face. Experiment results show our framework achieves better recognition accuracy than SIFT algorithm on FERET database.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1690-1704
• /
• 2013

An affine invariant descriptor is proposed, which is able to well represent the affine covariant regions. Estimating main orientation is still problematic in many existing method, such as SIFT (scale invariant feature transform) and SURF (speeded up robust features). Instead of aligning the estimated main orientation, in this paper ellipse orientation is directly used. According to ellipse orientation, affine covariant regions are firstly divided into 4 sub-regions with equal angles. Since affine covariant regions are divided from the ellipse orientation, the divided sub-regions are rotation invariant regardless the rotation, if any, of ellipse. Meanwhile, the affine covariant regions are normalized into a circular region. In the end, the gradients of pixels in the circular region are calculated and the partition-based descriptor is created by using the gradients. Compared with the existing descriptors including MROGH, SIFT, GLOH, PCA-SIFT and spin images, the proposed descriptor demonstrates superior performance according to extensive experiments.

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1894-1905
• /
• 1996

Delauuany triangulation which is the dual of Dirichlet tessellation is not affine invariant. In other words, the triangulation is dependent upon the choice of the coordinate axes used to represent the vertices. In the same reason, Delahanty tetrahedrization does not have an affine iveariant transformation property. In this paper, we present a new type of tetrahedrization of spacial points sets which is unaffected by translations, scalings, shearings and rotations. An affine invariant tetrahedrization is discussed as a means of affine invariant 2 -D triangulation extended to three-dimensional tetrahedrization. A new associate norm between two points in 3-D space is defined. The visualization of the structure of tetrahedrization can discriminate between Delaunay tetrahedrization and affine invariant tetrahedrization.

• Bulletin of the Korean Mathematical Society
• /
• v.38 no.1
• /
• pp.157-161
• /
• 2001

In this paper, we prove that an affine manifold M is finitely covered by a manifold $\overline{M}$ where $\overline{M}$ is radiant or the tangent bundle of $\overline{M}$ has a conformally flat vector subbundle of the projective holonomy group of M admits an invariant probability Borel measure. This implies that$x^M$is zero.

• Journal of the Chungcheong Mathematical Society
• /
• v.24 no.4
• /
• pp.825-832
• /
• 2011

In this paper, we make a minute and detailed proof of a part which is omitted in the process of obtaining the value of the curvature tensor for an invariant affine connection at the point {H} of a reductive homogeneous space G/H in the paper 'Invariant affine connections on homogeneous spaces' by K. Nomizu.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.517-519
• /
• 2004

This paper describes an approach to estimate a robot pose with an image. The algorithm of pose estimation with an image can be broken down into three stages : extracting scale-invariant features, matching these features and calculating affine invariant. In the first step, the robot mounted mono camera captures environment image. Then feature extraction is executed in a captured image. These extracted features are recorded in a database. In the matching stage, a Random Sample Consensus(RANSAC) method is employed to match these features. After matching these features, the robot pose is estimated with positions of features by calculating affine invariant. This algorithm is implemented and demonstrated by Matlab program.

• Journal of the Korean Mathematical Society
• /
• v.53 no.5
• /
• pp.1149-1165
• /
• 2016

In this paper, we show that there exists no left invariant Riemannian metric h on the Heisenberg group H such that (H, h) is a symmetric Riemannian manifold, and there does not exist any H-invariant metric $\bar{h}$ on the Heisenberg manifold $H/{\Gamma}$ such that the Riemannian connection on ($H/{\Gamma},\bar{h}$) is a Yang-Mills connection. Moreover, we get necessary and sufficient conditions for a group homomorphism of (SU(2), g) with an arbitrarily given left invariant metric g into (H, h) with an arbitrarily given left invariant metric h to be a harmonic and an affine map, and get the totality of harmonic maps of (SU(2), g) into H with a left invariant metric, and then show the fact that any affine map of (SU(2), g) into H, equipped with a properly given left invariant metric on H, does not exist.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1253-1272
• /
• 2010

In this paper, we propose a new affine shape adaptation scheme for the affine invariant feature detector, in which the convergence stability is still an opening problem. This paper examines the relation between the integration scale matrix of next iteration and the current second moment matrix and finds that the convergence stability of the method can be improved by adjusting the relation between the two matrices instead of keeping them always proportional as proposed by previous methods. By estimating and updating the shape of the integration kernel and differentiation kernel in each iteration based on the anisotropy of the current second moment matrix, we propose a coarse-to-fine affine shape adaptation scheme which is able to adjust the pace of convergence and enable the process to converge smoothly. The feature matching experiments demonstrate that the proposed approach obtains an improvement in convergence ratio and repeatability compared with the current schemes with relatively fixed integration kernel.

• International Journal of Contents
• /
• v.9 no.2
• /
• pp.1-7
• /
• 2013

This paper proposes an efficient matching algorithm based on ASIFT (Affine Scale-Invariant Feature Transform) which is fully invariant to affine transformation. In our approach, we proposed a method of reducing similar measure matching cost and the number of outliers. First, we combined the Manhattan and Chessboard metrics replacing the Euclidean metric by a linear combination for measuring the similarity of keypoints. These two metrics are simple but really efficient. Using our method the computation time for matching step was saved and also the number of correct matches was increased. By applying an Optimized Random Sampling Algorithm (ORSA), we can remove most of the outlier matches to make the result meaningful. This method was experimented on various combinations of affine transform. The experimental result shows that our method is superior to SIFT and ASIFT.