Time as essence for photo browsing through personal digital libraries

Abstract

We developed two photo browsers for collections with thousands of time-stamped digital images. Modern digital cameras record photo shoot times, and semantically related photos tend to occur in bursts. Our browsers exploit the timing information to structure the collections and to automatically generate meaningful summaries. The browsers differ in how users navigate and view the structured collections. We conducted user studies to compare the two browsers and a commercial image browser. Our results show that exploiting the time dimension and appropriately summarizing collections can lead to significant improvements. For example, for one task category, one of our browsers enabled a 33% improvement in speed of finding given images compared to the commercial browser. Similarly, users were able to complete 29% more tasks when using this same browser.

An Examination of a Large Visual Lifelog

“…There has been much research recently on the organization of personal photo archives [3,4,5]. Some of this research aims to organize personal photo archives by exploiting the results of visual content analysis of the photo in order to extract some semantic meaning, with the goal of aiding the organization, search and retrieval of the photos.…”

“…Most importantly and uniquely, this is the first time an individual has worn a SenseCam for such a prolonged period of time. The potential benefits of a personal visual diary such as that generated by a SenseCam have been detailed by Hodges et al [5] and include the maintenance of personal histories, security benefits by maintaining mobile visual logs and healthcare benefits, both for healthcare professionals and patients. …”

I-SEARCH: A Unified Framework for Multimodal Search and Retrieval

“…For example, in the PhotoMesa image browser [7], images in a directory are arranged in space filling boxes using a quantum Treemap algorithm. Clustering images by time is a popular way for organisation of personal collections [8]. In PhotoTOC [9] content based clustering is applied after time-based clustering for clusters that contain many images.…”

MyOwnLife: incremental and hierarchical classification of a personal image collection on mobile devices

“…Segmenting the sequence of time stamps has been viewed in [2,3] as the incremental detection of gaps. Some thresholding sets the definition of a "meaningful" gap.…”