Part surface roughness measuring method based on polarization imaging

The invention discloses a component surface roughness measuring method based on polarization imaging, which comprises the following steps: firstly, acquiring gray level images of four polarization angles on the surface of a roughness comparison sample block, calculating a polarization phase angle image of a roughness module according to a Stokes vector, extracting a to-be-measured area from the gray level images, and calculating a standard deviation of gray level values of pixels of the to-be-measured area; the standard deviation of different standard roughness modules is obtained in sequence, a least square fitting model is established, a standard deviation-roughness function model of the surface of the part is fitted, finally, the standard deviation of the to-be-measured target surface is calculated and substituted into the fitting function model, and the roughness value can be obtained. The method has the advantages of low cost, high precision and miniaturization. 本发明公开了一种基于偏振成像的零部件表面粗糙度测量方法，首先获取粗糙度对比样块表面四