Facial Expression Classification Using Rotation Slepian-based Moment Invariants

TL;DR

This paper introduces a new rotation invariant feature based on Slepian functions for facial expression classification, demonstrating robustness to noise and improved performance in pattern recognition tasks.

Contribution

It proposes a novel Slepian-based rotation moment invariant for image analysis, combining theoretical proof with practical experiments.

Findings

The Slepian-based moments are rotation invariant.

The proposed invariants are robust to noise.

They achieve good classification performance on real facial data.

Abstract

Rotation moment invariants have been of great interest in image processing and pattern recognition. This paper presents a novel kind of rotation moment invariants based on the Slepian functions, which were originally introduced in the method of separation of variables for Helmholtz equations. They were first proposed for time series by Slepian and his coworkers in the 1960s. Recent studies have shown that these functions have an good performance in local approximation compared to other approximation basis. Motivated by the good approximation performance, we construct the Slepian-based moments and derive the rotation invariant. We not only theoretically prove the invariance, but also discuss the experiments on real data. The proposed rotation invariants are robust to noise and yield decent performance in facial expression classification.