Edge detection of potential field interpretation is an important task． The traditional edge detection methods have poor ability in outlining weak amplitude anomalies clearly． The resolved edges position is blurred． We purposed new edge detection methods based on directional eigenvalues of potential field gradient tensor for the causative sources． In order to balance strong and weak amplitude anomalies simultaneously，we present one normalization method using different orders of vertical derivatives to improve the new filters． The presented fil- ters were tested on synthetic and real potential field data to verify its feasibility． All of the results have shown that the new edge detection methods can not only display the sources edges precisely and clearly，but also bring out more geological subtle details．