Selecting appropriate cutting parameters can enhance surface quality and extend component lifespan. In addressing challenges such as prolonged duration and low efficiency in multi-parameter turning experiments, constructing precise finite element models is the primary task. Subsequently, to obtain comprehensive distributions of the cutting force and temperature under various cutting parameters, an orthogonal turning experiment was designed, and numerical simulations were conducted. To acquire the surface roughness information of the machined surface, image processing techniques were introduced, encompassing surface mesh calibration, workpiece edge extraction, and edge fitting, with the aim of calculating surface roughness values based on the results of finite element simulation. An in-depth exploration of the interrelationships between the cutting parameters and cutting force, turning temperature, and surface roughness was conducted through range analysis and multiple-factor linear regression analysis. Consequently, a multivariate regression model was developed to address this relationship. Finally, the practical feasibility of the proposed method was verified through turning experiments. This study establishes a foundation for constructing linear regression models between workpiece surface quality and cutting parameters, and demonstrates the innovative application of image processing techniques to overcome the difficulties in obtaining and measuring workpiece surface quality.