Combining surface measurement data from individual measurements of surface fragments is an issue that has been recognized for flat surfaces. The connection takes place on the principle of making ‘overlap’ measurements according to a specific measurement strategy, and then the algorithm synthesizes the measurement data for the common part (data fusion). This paper presents a method of combining partial data into one larger set using image processing methods. The purpose of the analysis is to combine surface data of a more complex shape in terms of surface roughness and waviness. A successful attempt was made to combine surface measurement data located on a cylindrical surface – convex surface. A rotated table was designed and used for surface data acquisition. The datasets were acquired with the use of CCI 6000 (366 μm – 366 μm) with the assumed overlapping of at least 20%. The measurement datasets were first pre-processed: filling in non-measured points, levelling and form re- moving were applied. For such processed datasets, the common part was identified (data registration) and then the data fusion was performed. An example of stitching the surface datasets shows usefulness of the presented methodology.