We report on recent research undertaken in the framework of the Silvretta Archaeological Project, in which we are developing methods to detect certain types of archaeological ruins in remotely sensed images in order to assist archaeological survey. Our approach aims at assessing the probability of the presence of objects of our interest based on geometric cues that can be automatically detected in the satellite and aerial images that we use. We describe our methodology and the first integral step, constituting a new approach to texture segmentation that we developed to reduce the rate of false detections.