A new approach to object-related image retrieval

Image retrieval has been commonly attempted using non-semantic approaches. It is clear though, that semantic retrieval is more desirable because it fa cilitates the user's task. In this paper, we present a new approach to sema ntic access of a database of images by asking for the presence of certain o bjects; this is known as object-related image retrieval. This approach is built within a classical computer vision framework (i.e. l ocalization, segmentation and identification). Our approach first searches for the main areas of attention (most salient areas of an image) and then a pplies appearance-based methods to classify (index) all images by 'symbolic ' names. These names are referred to objects, which finally allows the use of semantics driven by these object names, e.g. retrieve '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. th eir 'correctness'. An experimental result using a database of 3000 images i s presented. (C) 2000 Academic Press