NeTra: A toolbox for navigating large image databases

We present here an implementation of NeTra, a prototype image retrieval sys tem that uses color, texture, shape and spatial location information in seg mented image regions to search and retrieve similar regions from the databa se. A distinguishing aspect of this system is its incorporation of a robust automated image segmentation algorithm that allows object- or region-based search. Image segmentation significantly improves the quality of image ret rieval when images contain multiple complex objects. Images are segmented i nto homogeneous regions at the time of ingest into the database, and image attributes that represent each of these regions are computed. In addition t o image segmentation, other important components of the system include an e fficient color representation, and indexing of color, texture, and shape fe atures for fast search and retrieval. This representation allows the user t o compose interesting queries such as "retrieve all images that contain reg ions that have the color of object A, texture of object B, shape of object C, and lie in the upper of the image", where the individual objects could b e regions belonging to different images. A Java-based web implementation of NeTra is available at http://vivaldi.ece.ucsb.edu/Netra.