Blur Invariants for Image Recognition

• DOI: 10.1007/s11263-023-01798-7
• Publication Date: 2023-06-01T07:02:41Z
• Authors: Jan Flusser; Matěj Lébl; Filip Šroubek; Matteo Pedone; Jitka Kostková
• Keywords: Deblurring; Gaussian blur

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