The relationships between laser speckle pattern texture features of grinding surface and surface roughness are investigated. The laser speckle pattern texture images of surface roughness are taken by a simple setup. Gauss-Markov random field (GMRF) model is a kind of texture model method which can describe probability model of gather of texture and be able to capture the local contextual information in an image. Therefore, by modeling GMRF model the laser speckle texture images of grinding surface are analyzed. Feature vectors of GMRF are calculated with different neighbor sets. Texture features- Mean, Variance and Energy are extracted to characterize grinding surface roughness from GMRF feature vectors. The relationships curves are drawn between the texture features and surface roughness. The experiment results show that the surface roughness contained in the surface speckle pattern texture images has a good monotonic relationship with texture features of GMRF model. This method can extract the surface roughness of the object surface composed of the same material and machined by the same method as the standard specimen.© (2010) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.