The optical perception of surfaces manufactured with high precision is an important quality feature for most products. The respective manufacturing process is rather complex and depends on a variety of process parameters which have a direct impact on the surface shape and topography in the most cases. Surface-shapes, topographies and colorings are mostly measured using classical methods (roughness measuring device, gloss measuring device, spectrophotometer, computer tomography, or tactile coordinate measuring instruments). To improve the conventional methods of condition monitoring, in this case represented by the monitoring of the surface, a new image processing approach is needed to get a faster and more cost-effective analysis of manufactured surfaces. For this reason, different optical techniques based on images have been developed over the past years. In this paper, a framework for surface monitoring is outlined and discussed in detail according to every single step along the monitoring process. For this purpose, the study differentiates between the application of the descriptive statistics as well as the application of artificial intelligence. Both applications are mainly based on the same data sources, though on different sample sizes and provide answers to differing questions that often complement each other.