Aria: An Agent for Annotating and Retrieving Images

Although modern photography has come a long way, the process of making and using photographs still requires more effort than it should. Using software agents rather than human labor can help reduce some of this tedium.Aria is an interface agent designed to assist users by proactively looking for opportunities for image annotation and retrieval. Although it doesn't completely automate image annotation and retrieval, Aria dramatically reduces user interface overhead, which can lead to better-annotated image libraries and fewer missed opportunities for image use.The authors designed Aria's interface agent to facilitate--rather than fully automate--the textual annotation and retrieval process. The agent's role lies not so much in automatically performing the annotation and retrieval but in detecting opportunities for performing these functions and alerting the user to those opportunities. The agent can also, when appropriate, help the user complete the operations.Future work will center on taking advantage of more opportunities to use context to determine appropriate situations for image annotation, image library browsing, and retrieval. The authors are often asked how their approach will scale to large image collections. Keywords could relate to ontologies and knowledge bases to do inheritance or simple inference searches. Aria's retrieval technology treats image sets as an unstructured database, but perhaps a better method would be to look at sets of pictures as linked networks. In the long run, the authors seek to capture and use commonsense knowledge about typical picture- taking situations.