OCT image blind despeckling based on gradient guided filter with speckle statistical prior

OCT images have been widely used for ocular diagnosis. However, speckles occur in OCT images due to the property of coherent imaging, inevitably affecting the visual quality. To alleviate this problem, we propose a gradient-guided speckle image filtering approach with structure enhancement for directly removing speckles. Specifically, the multiplicative property of speckle is incorporated into guided filtering procedure for modeling OCT images. To avoid getting trapped in image distortions, we employ gradient regularization to integrate the structure information into the guided speckle image filtering procedure. Additionally, we introduce the statistical property of speckle noise obeying a gamma distribution into the least square method solver for the resulting non-convex GGSF. Experimental results validate the effectiveness of the GGSF for OCT image despeckling in comparison with state-of-the-art methods. Furthermore, we validate the benefits of GGSF for subsequent clinical analysis.