In this paper, we proposed a rotation invariant image descriptor based on Radon transform (RT) and energy operator. Radon transform captures the directional features of the pattern image by projecting the pattern onto different orientation slices, and its most attractive ability is to transform rotational components to circular shift components. Meanwhile, the energy operator can remove the cir...

We prove that every Kähler metric, whose potential is a function of the timelike distance in the flat Kähler-Lorentz space, is of quasi-constant holomorphic sectional curvatures, satisfying certain conditions. This gives a local classification of the Kähler manifolds with the above mentioned metrics. New examples of Sasakian space forms are obtained as real hypersurfaces of a Kähler space form ...

A new optical transformation that combines geometrical coordinate transformations with the conventional optical Fourier transform is described. The resultant transformations are invariant to both scale and rotational changes in the input object or function. Extensions of these operations to optical pattern recognition and initial experimental demonstrations are also presented.

This paper i n d u c e s a new neural network architecture for rotationally invariant object recognition. Second-order neurons are used in combination with polar sampling to obtain invariance without incurring excessive network size. Multiple experiments are presented demonsmting that incorporation of a variable range of rotational invariance results in impved performance over existing methods.

Local Parameter Histograms (LPH) based on Gaussian Markov random fields (GMRFs) have been successfully used in effective texture discrimination. LPH features represent the normalized histograms of locally estimated GMRF parameters via local linear regression. However, these features are not rotation invariant. In this paper two techniques to design rotation invariant LPH texture descriptors are...

The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribution through weight sharing. Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere. Examples include climate and weather science, astrophysics, and ...

Present paper demonstrates on innovative approach for a fundamental problem in computer vision to map real time a pixel in one image to a pixel on another image of the same scene, which is generally called image correspondence problem. It is a novel real time image matching method which combines Rotational Invariant Feature Selection for real time images and optimization capabilities of Hopfiel...

We present a new particle tracking algorithm for accurately resolving large deformation and rotational motion fields, which takes advantage of both local global algorithms. call this method ScalE Rotation Invariant Augmented Lagrangian Particle Tracking (SerialTrack). This builds an iterative scale rotation invariant topology-based feature vector each within multi-scale algorithm. The kinematic...

This paper presents the fusion of monogenic signal processing and differential geometry to enable monogenic analyzing of local intrinsic 2D features of low level image data. New rotational invariant features such like structure and geometry (angle of intersection) of two superimposed intrinsic 1D signals will be extracted without the need of any steerable filters. These features are important f...

A new invariant formulation of 3D eye-head kinematics improves on the computational advantages of quaternions. This includes a new formulation of Listing’s Law parameterized by gaze direction leading to an additive rather than a multiplicative saccadic error correction with a gaze vector difference control variable. A completely general formulation of compensatory kinematics characterizes arbit...