Author_Institution :
Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA
Abstract :
We describe a system for searching your personal photos using an extremely wide range of text queries, including dates and holidays ("Halloween"), named and categorical places ("Empire State Building" or "park"), events and occasions ("Radiohead concert" or "wedding"), activities ("skiing"), object categories ("whales"), attributes ("outdoors"), and object instances ("Mona Lisa"), and any combination of these -- all with no manual labeling required. We accomplish this by correlating information in your photos -- the timestamps, GPS locations, and image pixels -- to information mined from the Internet. This includes matching dates to holidays listed on Wikipedia, GPS coordinates to places listed on Wikimapia, places and dates to find named events using Google, visual categories using classifiers either pre-trained on ImageNet or trained on-the-fly using results from Google Image Search, and object instances using interest point-based matching, again using results from Google Images. We tie all of these disparate sources of information together in a unified way, allowing for fast and accurate searches using whatever information you remember about a photo. We quantitatively evaluate several aspects of our system and show excellent performance in all respects. Please watch a video demonstrating our system in action on a large range of queries at http://youtu.be/Se3bemzhAiY.
Keywords :
Global Positioning System; Internet; content-based retrieval; geographic information systems; search engines; GPS coordinates; GPS locations; Google Image Search; ImageNet; Internet; Wikimapia; Wikipedia; dates matching; holidays; image pixels; information correlation; interest point-based matching; personal photo searching; photo organization; photo recall; text queries; timestamps; visual categories; Global Positioning System; Google; Indexing; Internet; Manuals; Search problems; Visualization; content-based image retrieval; events; gps; image search; on-the-fly visual classification; photo organization;