Methods (105), apparatuses (600), and computer readable storage mediums for processing captured images having geolocations related to the captured images at the time of capture are disclosed. A representative geolocation is associated (110) with each group of images previously captured at the same location. For each representative geolocation, based on at least the timestamp of the images associated with the representative geolocation, the probability is determined (120) that a further image will be captured at or near the representative geolocation. For representative geolocations with a determined probability above a predetermined threshold, the respective representative geolocation is associated (130) with at least one personal place.