Abstract
We explore the use of soft computing and user defined classifications in multimedia database systems for contentbased queries. With multimedia databases, due to subjectivity of human perception, an object may belong to different classes with different probabilities (“soft ” membership), as opposed to “hard ” membership supported by conventional database systems. Therefore, we propose a unified model that captures both hard and soft memberships. In practice, however, in the process of implementing our model by extending a conventional database system, we increase the query processing complexity significantly. To remedy for this increase, we propose a variety of techniques to scale down the complexity by orders of magnitude.