DeepAI AI Chat
Log In Sign Up

On the Realization and Analysis of Circular Harmonic Transforms for Feature Detection

07/29/2019
by   Hugh L. Kennedy, et al.
5

Cartesian-separable realizations of circular-harmonic decompositions for angular spectrum estimation are presented and a powerful test-statistic for rotation-invariant feature-detection in images is proposed. The resulting steerable filters with a finite impulse response (FIR) have a low computational complexity. The test statistic is used to detect wedges, i.e. corners of arbitrary angle and unknown orientation, in synthetic and real imagery.

READ FULL TEXT

page 4

page 7

page 8

12/14/2016

Harmonic Networks: Deep Translation and Rotation Equivariance

Translating or rotating an input image should not affect the results of ...
03/12/2020

Arbitrary-Oriented Object Detection with Circular Smooth Label

Arbitrary-oriented object detection has recently attracted increasing at...
05/21/2021

Rotation invariant CNN using scattering transform for image classification

Deep convolutional neural networks accuracy is heavily impacted by rotat...
12/10/2021

On torque computation in electric machine simulation by harmonic mortar methods

The use of trigonometric polynomials as Lagrange multipliers in the harm...
01/09/2014

Efficient unimodality test in clustering by signature testing

This paper provides a new unimodality test with application in hierarchi...
10/26/2014

On Chord and Sagitta in Z^2: An Analysis towards Fast and Robust Circular Arc Detection

Although chord and sagitta, when considered in tandem, may reflect many ...