Blur Invariants for Image Recognition

TL;DR

This paper introduces a unified theory of blur invariants for image recognition that does not require prior knowledge of the blur type, enabling recognition of blurred images without deblurring.

Contribution

The paper presents a novel, comprehensive framework for blur invariants that generalizes previous methods and improves recognition robustness without needing blur type information.

Findings

All previous blur invariants are special cases of this approach.

The proposed invariants outperform existing methods in experiments.

Efficient and stable computation via Fourier domain and moment expansion.

Abstract

Blur is an image degradation that is difficult to remove. Invariants with respect to blur offer an alternative way of a~description and recognition of blurred images without any deblurring. In this paper, we present an original unified theory of blur invariants. Unlike all previous attempts, the new theory does not require any prior knowledge of the blur type. The invariants are constructed in the Fourier domain by means of orthogonal projection operators and moment expansion is used for efficient and stable computation. It is shown that all blur invariants published earlier are just particular cases of this approach. Experimental comparison to concurrent approaches shows the advantages of the proposed theory.