Method based on bioinspired sample improves autofocusing performances

In order to solve the issue between fast autofocusing speed and high volume data processing, we propose a bioinspired sampling method based on a retina-like structure. We develop retina-like models and analyze the division of sampling structure. The optimal retina-like sample is obtained by analyzing two key parameters (sectors and radius of blind area) of the retina-like structure through experiments. Under the typical autofocus functions, including Vollath-4, Laplacian, Tenengrad, spatial frequency, and sum-modified-Laplacian (SML), we carry out comparative experiments of computation time based on the retina-like sample and a traditional uniform sample. The results show that the retina-like sample is suitable for those autofocus functions. Based on the autofocus function of SML, the average time of uniform sample decreases from 3.5 to 2.1 s for the retina-like sample.