No abstract

Abstract. This paper discusses a framework for image retrieval. Most current systems are based on a single technique for feature extraction and similarity search. Each technique has its advantages and drawbacks concerning the result quality. Usually they cover one or two certain features of the image, e.g. histograms or shape information. The proposed framework is designed to be highly flexible, even if performance may suffer. The aim is to give people a platform to implement almost any kind of retrieval issues very quickly, whether it is content based or somehing else. The second advantage of the framework is the possibility to change retrieval characteristics within the program completely. This allows users to configure the ranking process as needed.

No abstract

One of the most important bits of every search engine is the query interface. Complex interfaces may cause users to struggle in learning the handling. An example is the query language SQL. It is really powerful, but usually remains hidden to the common user. On the other hand the usage of current languages for Internet search engines is very simple and straightforward. Even beginners are able to find relevant documents. This paper presents a hybrid query language suitable for both image and text retrieval. It is very similar to those of a full text search engine but also includes some extensions required for content based image retrieval. The language is extensible to cover arbitrary feature vectors and handle fuzzy queries.