Efficient and Effective Querying by Image Content

In the Q31C (Query By Image Content) projec we are studying methods to query large on-line image databeas using the images' content as the basis of the queries. Examples of the content we use include color, texture, sketch, snd shape of image objects and regions. Potential applications incude medical ("Give me other images that contain a tumor with a texture like this one"), photo-journalism( "Give me images that have blue at the top and red at the bottom"), and many others in art, fashion, cataloging, retailing, and industry.

We describe a set of novel features and similarity measures allowing query by image content, together with the QBIC system we implemented. We demonstrate the effectiveness of our system with normalized precision and recall experiments on test databases containing over 1000 images and 1000 objects populated from commercially available photo clip art images, and of images of airplane silhouettes. We also present novel methods for efficient processing of QBIC types of queries, that consist of filtering and indexing steps. We are specificaily addressing two problems: (a) non-Euclidean distance measures; and (b) high dimensionality of feature vectors. For the first problem, we introduce a new theorem at makes efficient filtering possible by bounding the non-Euclidean, full cross-term quadratic distance expression with a simple Euclidean distance. For the second, we illustrate how orthoganal transforms, such as the Karhunen Loeve transform, can help reduce the dimensionality of the search space. Our methods are general and allow some "false alarms" ( "false hits", or "false positives") but no false dismissals.

The resulting QBIC system offers effective retrieval using image content, and for large image dalabases significant speedup over straightforward indexing alternatives. The system is implemented in X/Motif and C running on an RS/6000,