Investigating human behaviors in selecting personal photos to preserve memories

Photos are excellent means for keeping and refreshing memories. Digital photography, however, imposes new challenges for keeping photos accessible on the long run due to threats such as hard disk crashes, format changes, or storage medium decay. Safe long-term preservation, ensuring the longevity of photos, comes at a cost, suggesting a restriction of this investment to the most valuable photos. Therefore, understanding how people behave when selecting their most valuable photos from large collections is an important first step towards the development of automatic preservation approaches. In this paper, we conduct a user study of 35 participants in selecting personal photos for long-term preservation. The results of the study provide insights for the photo selection process. In addition, we propose a photo selection method based on machine learning and compared human selections with leading edge clustering techniques, highlighting significant issues in emulating human decision patterns.