A picture is worth a thousand keywords: image-based object search on a mobile platform
2005 (English)In: CHI ’05 extended abstracts on Human factors in computing systems, 2005, 2025-2028 p.Conference paper (Refereed)
Finding information based on an object’s visual appearance is useful when specific keywords for the object are not known. We have developed a mobile image-based search system that takes images of objects as queries and finds relevant web pages by matching them to similar images on the web. Image-based search works well when matching full scenes, such as images of buildings or landmarks, and for matching objects when the boundary of the object in the image is available. We demonstrate the effectiveness of a simple interactive paradigm for obtaining a segmented object boundary, and show how a shape-based image matching algorithm can use the object outline to find similar images on the web.
Place, publisher, year, edition, pages
2005. 2025-2028 p.
content-based image retrieval, interactive segmentation, mobile interface, object recognition
Human Computer Interaction Computer Vision and Robotics (Autonomous Systems)
Research subject SRA - ICT
IdentifiersURN: urn:nbn:se:kth:diva-77740DOI: 10.1145/1056808.1057083OAI: oai:DiVA.org:kth-77740DiVA: diva2:501935
CHI EA ’05