VDM Chen, C: Episodic Memory For Browsing Personal Photographs

As personal digital photographs are used more and more, people may have difficulty in finding their own digital images in large of collections. Traditional approaches to search digital photographs are based on manual keyword indexing of images with text that describes the content of the images for subsequent retrieval. However, manual keyword indexing is too time consuming. This book provided a new idea which considered human episodic memory for image retrieval to improve personal imaging searching usability. Time and location are the main factors in human episodic memory; this book combined these types of data for clustering personal photos into events by a clustering model. This book also used these types of data to annotate personal images with keywords. It means the images can either be manually annotated with a set of keywords chosen by the owner of the collection, or keywords can be automatically inferred from the time and location stamps associated with the image and the Geographic Names Database Gazetteer.