Angular Accuracy of Steerable Feature Detectors

TL;DR

This paper investigates the fundamental limits of estimating the orientation of patterns in noisy images using steerable filters, proposing optimal subspace selection and validating the theoretical bounds through experiments.

Contribution

It introduces a statistical framework based on the CRLB for orientation estimation with steerable filters, including optimal component selection and experimental validation.

Findings

CRLB provides a fundamental accuracy limit for orientation estimation.

Optimal subspace selection improves estimation performance.

Experimental results match the theoretical CRLB predictions.

Abstract

The detection of landmarks or patterns is of interest for extracting features in biological images. Hence, algorithms for finding these keypoints have been extensively investigated in the literature, and their localization and detection properties are well known. In this paper, we study the complementary topic of local orientation estimation, which has not received similar attention. Simply stated, the problem that we address is the following: estimate the angle of rotation of a pattern with steerable filters centered at the same location, where the image is corrupted by colored isotropic Gaussian noise. For this problem, we use a statistical framework based on the Cram\'{e}r-Rao lower bound (CRLB) that sets a fundamental limit on the accuracy of the corresponding class of estimators. We propose a scheme to measure the performance of estimators based on steerable filters (as a lower bound), while considering the connection to maximum likelihood estimation. Beyond the general results, we analyze the asymptotic behaviour of the lower bound in terms of the order of steerablility and propose an optimal subset of components that minimizes the bound. We define a mechanism for selecting optimal subspaces of the span of the detectors. These are characterized by the most relevant angular frequencies. Finally, we project our template to a basis of steerable functions and experimentally show that the prediction accuracy achieves the predicted CRLB. As an extension, we also consider steerable wavelet detectors.