Semantic access to a database of images: an approach to object-related image retrieval
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 624-629
- https://doi.org/10.1109/mmcs.1999.779272
Abstract
Image retrieval has commonly been attempted using non-semantic approaches. It is clear though, that semantic retrieval is more desirable because it facilitates the user's task. We present a new approach to semantic access of a database of images by asking for the presence of certain objects; this is known as object-related image retrieval. This approach is built within a classical computer vision framework (i.e. localization, segmentation and identification). This platform is used to automatically index images of a given database by object names, which finally allows the use of semantics (driven by these object names) to extract images from the database (e.g. "all those images that have a bull and Melissa's face"). The use of a totally automatic system would cause some errors of indexing (and so retrieval). To solve this we use a human-in-the-loop strategy where a human expert is placed after the two outputs of the system to confirm their "correctness". An experimental result using a database of 1,300 images is presented.Keywords
This publication has 5 references indexed in Scilit:
- VisionPublished by MIT Press ,2010
- Structural Saliency: The Detection Of Globally Salient Structures using A Locally Connected NetworkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Texture frame curves and regions of attention using adaptive non-cartesian networksPattern Recognition, 1999
- Content-centric computing in visual systemsPublished by Springer Nature ,1997
- The design and use of steerable filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991