The object-oriented knowledge representation is considered as a natural and effective approach. Nevertheless, the use of object-oriented within complex image analysis has not undergone a rapid growth as it happened in...
详细信息
ISBN:
(纸本)0819440086
The object-oriented knowledge representation is considered as a natural and effective approach. Nevertheless, the use of object-oriented within complex image analysis has not undergone a rapid growth as it happened in other fields. We argue that one of the major problems comes form the difficulty of conceiving a comprehensive framework for coping with the different abstraction levels and the vision task operations. With the goal to overcome such a drawback, we present a new knowledge model for medical image content analysis based on the object-oriented paradigm. The new model abstracts common properties from different types of medical images by using three attribute parts: description, component, and semantic graph, and also specifies its actions to schedule the detection procedure, properly deform the shape of model components to match the corresponding anatomies in images, select the best match candidates, and verify combination graphs from detected candidates with the semantic graph defined in the model. The performance of the proposed model has been tested on pelvis digital radiographs. Initial experimental results are encouraging.
object-oriented (O-O) data models are known for their rich semantics and modeling power for representing complex data. It is also generally agreed that O-O models can provide more functionalities and semantic construc...
详细信息
object-oriented (O-O) data models are known for their rich semantics and modeling power for representing complex data. It is also generally agreed that O-O models can provide more functionalities and semantic constructs for modeling data in applications of geographic information systems (GIS). However, there is a lack of a complete understanding of how to apply O-O concepts in modeling GIS data. In this paper, we propose an object-oriented data model called OMEGA which is designed especially for GIS applications. We discuss in the model the use of O-O concepts in characterizing GIS applications. This model distinguishes geographic data into three major types: geometric objects, geographic objects, and relationship objects. Each of these types of objects is modeled by distinct and proprietary type hierarchies. In the core OMEGA model, there are five semantic association types: generalization, aggregation, (spatial) relationship, geographic constituent set (GCS), and selective aggregation (SA). The major enhancements that have been added to the model include (1) separating of relationships between objects from the object class and grouping of relationships of the same type into a relationship class;these classes can have aggregation as well as generalization associations;(2) a proposed unique set construct, called a geographic constituent set (GCS), especially for modeling of GIS data;and, (3) a proposed selective aggregation (SA) construct which is used to resolve overrefinement problems in a generalization hierarchy. Properties associated with these new constructs are also presented.
暂无评论