Multi-module collaborative optimization-driven fast speckle correlation imaging in variable environments

Speckle correlation imaging based on the optical memory effect provides a valuable approach for non-invasive imaging through scattering media, yet its practical implementation faces significant challenges in reconstruction speed. To overcome these challenges, a fast speckle correlation imaging (FSCI) algorithm that incorporates three key technical innovations is presented in this paper. The method commences with the intelligent sub-speckle quality control and initialization adaptation (ISQIA) module, which integrates two core functional sub-modules: one is sub-speckle screening (SS), which eliminates low-information sub-speckles based on the entropy-contrast criteria; the other is adaptive initialization (AI), which selects optimal sub-speckles to accelerate the convergence of subsequent calculations. The reconstruction accuracy is further enhanced through weighted coherent averaging (WCA), which utilizes cross-correlation peaks as weighting coefficients. Finally, dynamic iteration termination (DIT) automatically halts computation when reconstruction changes become negligible, thus optimizing computational efficiency. Experimental results show that the FSCI algorithm is 40.9% faster than traditional speckle correlation imaging methods, taking only 3.13 s for reconstruction in darkrooms. It also improves imaging quality significantly: PSNR reaches 27.04 dB, and SSIM is improved to 0.87. Notably, FSCI performs stably in weak to extremely strong noise (SNR 1.79 to -5.78dB), excels at recovering complex structures like Chinese characters, and thus has high application potential in fields such as biomedical imaging and industrial non-destructive testing.