Regular detection of cracks on the road surface is a necessary link to ensure the safety of road users. There are several traditional methods that have been developed to detect road cracks, but there are still many shortcomings in these traditional methods. The inefficiency of conventional methods has led to the development of automatic detection methods using image processing. This research aims to detect road surface cracks using the thresholding method, median filter, and morphological techniques applied to 40 road surface images which are divided into training data and test data. Processing image data for road surface crack detection in this research uses the Open CV tool. From these results it was found that this method can be applied with a success rate of 85%.