The algorithm of automated karst depression recognition uses a digital terrain model (DTM) and mainly applies the methods of moving window with a kernel size of 3 x 3 cells using focal functions. It is divided into four parts: watershed calculation, depression delineation, higher lever depression delineation and non-karst depression elimination. The essential part of algorithm is delineation of depression by the elevation of the lowest border cell of watershed. Depressions of higher level are recognised by filling previously recognised depressions. Performance of algorithm was tested on test area in Kras region (Slovenia) using DTMs with spatial resolution of 12.5 m and 3 m. The results mainly depend on the DTM characteristics and quality, especially on their spatial resolution.