Abstract The goal of integration is to utilize a spatial model of an object obtained from the cloud of points and, possibly, to support it with a photogrammetric model in those places, where scanner measurements may be hard to perform, or even impossible. Since the image offers a possibility of texturing objects obtained most often from digital metric images, integration makes it possible to create a model of a view resembling the actual one. Another advantage of a photogrammetric model is the possibility of obtaining object edges with high accuracy (due to, among other things, the application of sub-pixel algorithms). It is just that aspect which, in relation to scanning, is described in the paper. The correctness of locating objects, which have been extracted from points, is tested by placing them on a photogrammetric model. In the proposed method, the authors tested extraction of objects, which was based on methods using the first and the second derivatives of a digital image. Those algorithms had been developed and tested earlier in many engineering projects that were based on a multilevel analysis of digital images. Research works were performed on several selected test facilities, located in the open-air ethnographic museum at Tokarnia, Poland.