DocumentCode :
341887
Title :
Semantic access to a database of images: an approach to object-related image retrieval
Author :
Martinez, Aleix ; Serra, Joan R.
Author_Institution :
Robot Vision Lab., Purdue Univ., West Lafayette, IN, USA
Volume :
1
fYear :
1999
fDate :
36342
Firstpage :
624
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 :
database indexing; image retrieval; multimedia databases; visual databases; computer vision; errors; experimental result; human-in-the-loop strategy; image database semantic access; image indexing; object names; object-related image retrieval; semantic retrieval; Computer vision; Focusing; Humans; Image databases; Image retrieval; Image segmentation; Indexes; Indexing; Information retrieval; Robot vision systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia Computing and Systems, 1999. IEEE International Conference on
Conference_Location :
Florence
Print_ISBN :
0-7695-0253-9
Type :
conf
DOI :
10.1109/MMCS.1999.779272
Filename :
779272
Link To Document :
بازگشت