A Retrieval System for Coats of Arms
نویسندگان
چکیده
The paper describes a project aiming at content-based retrieval of coats of arms to facilitate information finding. The retrieval system should be usable by experts and by casual users. In order to make use of the specific nature of arms about 20 different features have been developed to allow an expert to fine-tune an image search. For the casual user different features are grouped into feature lists that are called query models. These models correspond to image clusters in the database. The paper discusses the customization of features for the retrieval of coats of arms and their grouping into query models. Experiments and test results show a good performance of query models. keywords: content-based image retrieval, image databases, coats of arms.
منابع مشابه
Content-based image retrieval of coats of arms
The paper describes a content-based image retrieval system for coats of arms. The characteristics of arms are analyzed and specific features for segmentation, object layout, symmetry, etc. developed and implemented. Search queries are formulated and classified into query models which represent similarity of images by the features they use. These models are rated by recall and precision.
متن کاملJEmblazoner: Konstruktion von Wappenbildern aus textuellen Beschreibungen JEmblazoner: Construction of Coats of Arms Images from Textual Descriptions
This paper describes the free software component JEmblazoner. JEmblazoner is a Java-based user interface for Content-based Image Retrieval (CBIR) in databases of coats of arms images. JEmblazoner allows to create coats of arms images from textual descriptions (socalled Blazons) that can be used as input for CBIR queries. In CBIR image databases are queried by qualitative features without the as...
متن کاملFlorentine Coats of Arms on the Web: Experimenting with Retrieval Based on Text or Image Content
The paper describes two different ways of accessing a collection of Florentine coats of arms, which was digitised and made available on the Web. One way is a traditional approach: textual description and indexing. As heraldry uses a specific and complex terminology the textual approach seemed alright for experts but insufficient for laypersons. Therefore an additional retrieval mode was chosen ...
متن کاملAutomatic Query Generation for Content-Based Image Retrieval
We describe a subsystem of a content-based image retrieval (CBIR) environment that supports a user in the definition of image similarity. Out of a single image or a set of query images we refine a query model: a list of feature extraction functions with associated thresholds and weights. The subsystem aims at bridging the gap between a user’s high-level concepts and the low-level visual feature...
متن کاملThe Web Database of Florentine Coats of Arms a Project to Identify Complex Image Content Using Both Indexing and Pattern Recognition
The paper describes a collection of Florentine coats of arms, which was digitised and made accessible on the Web. In addition to the traditional approach of textual description and indexing, an additional retrieval mode was chosen based on the visual specification by users of the content of images representing the coat of arms. This seems an interesting alternative for two reasons. Firstly, the...
متن کامل