An Algorithm which Automatically Constructs Discrimination Graphs in a Visual Knowledge Base
نویسنده
چکیده
Model-based vision systems must be capable of dealing with large quantities of hypothetical interpretations. Hypothesise-and-test methods often lead to combinatorial explosions of possible interpretations. Discrimination graphs prevent such explosions by imposing a hierarchical organisation on the domain of interpretation. Such an organisation effectively reduces the number of interpretations that the system has to deal with. This paper presents an algorithm which automatically constructs discrimination graphs.
منابع مشابه
Automatic Generation and Evaluation of Sentence Graphs out of Word Graphs
This paper reports on the development of a system that automatically constructs representations of the meaning of sentences using rules of grammar and a dictionary of word meanings. The meanings of words and sentences are expressed using an extension of knowledge graphs, a semantic network formalism. Furthermore the system contains an algorithm that calculates an evaluation measure for alternat...
متن کاملA Study of Automatically Acquiring Explanatory Inference Patterns from Corpora of Explanations: Lessons from Elementary Science Exams
Our long term interest is in building inference algorithms capable of answering questions and producing human-readable explanations by aggregating information from multiple sources and knowledge bases. Currently information aggregation (also referred to as “multi-hop inference”) is challenging for more than two facts due to “semantic drift”, or the tendency for natural language inference algori...
متن کاملAn Ant Colony Optimization Algorithm for Network Vulnerability Analysis
Intruders often combine exploits against multiple vulnerabilities in order to break into the system. Each attack scenario is a sequence of exploits launched by an intruder that leads to an undesirable state such as access to a database, service disruption, etc. The collection of possible attack scenarios in a computer network can be represented by a directed graph, called network attack gra...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کامل