• Corpus ID: 6414284

Modeling Shapes and Graphics Concepts in an Ontology

  title={Modeling Shapes and Graphics Concepts in an Ontology},
  author={Mehdi Niknam and Christel Kemke},
This work presents the development of a graphics ontology for natural language interfaces. In a first phase, the ontology was developed in a standard way, based on documentations and textbooks for graphics systems as well as existing ontologies. In the second phase, we collected sets of natural language instructions to create and modify graphic images from human subjects. In these sentences, people describe actions to create or modify images; graphic objects and shapes; and features of shapes… 

Figures and Tables from this paper

An Investigation into OWL for Concrete Syntax Specification Using UML Notations
OWL for visual language specification is explored by specifying the concrete syntax of selected UML class diagram notations in an ontology by using the automated instance classification feature of ontology reasoners.
Shapes as property restrictions and property-based similarity
This work looks into the details of modeling shapes in an ontology as property restrictions on classes and uses the adequate similarity measure based on properties which helps find similar shapes in different contexts, depending on the relevance of the properties in the particular situation.
A novel computer algorithm has been proposed to generate random path between two points in space and an ontology has been developed that describes the domain of discourse to provide an optimized generation of best points that are closer to the target point.
Texture Retrieval in the Wild through detection-based attributes
This paper refers to Texel-Att, a recent texel-based descriptor which has shown to capture fine grained variations of a texture, for retrieval purposes, and shows that this descriptor is robust to distortions resulting from acquisitions in the wild.
Texel-Att: Representing and Classifying Element-Based Textures by Attributes
Texel-Att is the first fine-grained, attribute-based representation and classification framework for element-based textures, and individuates texels, characterizing them with individual attributes; subsequently, texels are grouped and characterized through layout attributes, which give the Texel-att representation.
SIMCO: SIMilarity-based object COunting
SIMCO is presented, a completely agnostic multiclass object counting approach that provides state-of-the-art scores on counting benchmarks and that it can also help in many challenging image understanding tasks.
ELEMENT-BASED TEXTURES 3 TEXEL DETECTOR MaskRCNN trained on ElBa training set Texture Image INDIVIDUAL DESCRIPTION Texel position and categories , Size , Appearance Texels TEXEL GROUPING Grouping by Texel Category Individual Descriptors LAYOUT DESCRIPTION Homogeneity
Texel-Att is the first fine-grained, attribute-based representation and classification framework for element-based textures, and individuates texels, characterizing them with individual attributes; subsequently, texels are grouped and characterized through layout attributes, which give the Texel-att representation.
Visual Syntax of UML Class and Package Diagram Constructs as an Ontology
This work specifies the visual syntax of a set of UML class and package diagram constructs as an ontology in the Web ontology language, OWL, and demonstrates the general value of using OWL for visual syntax specifications.
Data Analytics and Management in Data Intensive Domains: 21st International Conference, DAMDID/RCDL 2019, Kazan, Russia, October 15–18, 2019, Revised Selected Papers
This paper will discuss three approaches to combining neural networks with algorithms: structured pooling, unrolling of algorithm iterations into network layers and explicit differentiation of the output w.r.t. the input.
Applied Ontologies for Managing Graphic Resources in Spectroscopy
The report presents the tasks on graphical resources management thoroughly describing applied ontologies of GrafOnto research graphics collection used for solving problems of spectroscopy. The


Finite State Grammar Transduction from Distributed Collected Knowledge
This work validates the use of a web based knowledge capture system to harvest phrases to build grammar models and compares the task recognition performance of this FSGT model with an n-gram Statistical Language Model (SLM).
A survey of the state of the art in ontology evaluation is presented, typically in order to determine which of several ontologies would best suit a particular purpose.
Attention to Endpoints: A Cross-Linguistic Constraint on Spatial Meaning
It is shown that people discriminate the endpoints of spatial motion events more readily than they do event beginnings-suggesting a non-linguistic attentional bias toward endpoints, consistent with the proposal that event endpoints are privileged over event beginnings, in both language and perception.
Knowledge Processes and Ontologies
An approach for ontology-based knowledge management (KM) that includes a tool suite and a methodology for developing ontological-based KM systems is presented, illustrated by CHAR (Corporate History AnalyzeR), a KM system for corporate history analysis.
Language, Thought, and Reality: Selected Writings of Benjamin Lee Whorf
The pioneering linguist Benjamin Whorf (1897--1941) grasped the relationship between human language and human thinking: how language can shape our innermost thoughts. His basic thesis is that our
Accurate Unlexicalized Parsing
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence
Development of a Graphics Ontology for Natural Language Interfaces
  • MS thesis. The University of Manitoba, Winnipeg,
  • 2010
Toward principles for the design of ontologies used for knowledge sharing?
  • T. Gruber
  • Computer Science, Philosophy
    Int. J. Hum. Comput. Stud.
  • 1995
The role of ontology in supporting knowledge sharing activities is described, and a set of criteria to guide the development of ontologies for these purposes are presented, and it is shown how these criteria are applied in case studies from the design ofOntologies for engineering mathematics and bibliographic data.
Common Sense Data Acquisition for Indoor Mobile Robots
This work describes the collection of common sense data through the Open Mind Indoor Common Sense website and discusses active desire selection based on current beliefs and commands and a room-labeling application based on probability estimates from the common sense knowledge base.