特徴抽出の研究

特徴抽出とは、生データを圧縮して、便利な表現に変換する貴重な情報処理の分野の一つである。本研究は、パッチマッチングなどの様々な課題にたいして応用し、よりいい特徴の抽出することを目指す。

  • Siameseネットワークモデルを用いた画像特徴量抽出

    Siameseネットワークモデルを用いた画像特徴量抽出

    Siameseネットワークモデルを効率的に学習させることで、 ロバストな画像特徴量を計算する手法を提案する。 提案手法では、モデルに2つの画像パッチを入力し、出力された特徴量の誤差によってモデルを学習させる。 また、入力するパッチをその識別の難しさによって分類し、識別が困難なパッチを優先的に学習させることで、SIFT特徴量よりもロバストな特徴量の抽出を実現した。

  • 測地混合モデル

    測地混合モデル

    There are many cases in which data is found to be distributed on a Riemannian manifold. In these cases, Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. For this purpose, we draw inspiration on a variant of the expectation-maximization algorithm, that uses a minimum message length criterion to automatically estimate the optimal number of components from multivariate data lying on an Euclidean space. In order to use this approach on Riemannian manifolds, we propose a formulation in which each component is defined on a different tangent space, thus avoiding the problems associated with the loss of accuracy produced when linearizing the manifold with a single tangent space. Our approach can be applied to any type of manifold for which it is possible to estimate its tangent space.

  • 変形・照明不変の特徴量

    変形・照明不変の特徴量

    DaLI descriptors are local image patch representations that have been shown to be robust to deformation and strong illumination changes. These descriptors are constructed by treating the image patch as a 3D surface and then simulating the diffusion of heat along the surface for different intervals of time. Small time intervals represent local deformation properties while large time intervals represent global deformation properties. Additionally, by performing a logarithmic sampling and then a Fast Fourier Transform, it is possible to obtain robustness against non-linear illumination changes. We have created the first feature point dataset that focuses on deformation and illumination changes of real world objects in order to perform evaluation, where we show the DaLI descriptors outperform all the widely used descriptors.

論文

  • 3D Human Pose Tracking Priors using Geodesic Mixture Models
  • Fashion Style in 128 Floats: Joint Ranking and Classification using Weak Data for Feature Extraction
  • Discriminative Learning of Deep Convolutional Feature Point Descriptors
  • Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking
  • DaLI: Deformation and Light Invariant Descriptor
  • Geodesic Finite Mixture Models

ソフトウェア

  • GFMM
  • StyleNet
  • Deep Descriptor
  • DaLI
  • ceigs

データセット

  • DaLI Dataset
    • DaLI Dataset
    • Local image patch feature descriptor illumination and deformation invariance evaluation dataset.