FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W150398843> ?p ?o ?g. }

• W150398843 abstract "This thesis concentrates in the fields of computer vision, image understanding and machine learning. We present a novel approach for learning visual concepts from raw image data. Our method is able to learn new concepts and, in result, acquire knowledge that can be than used in standard computer vision tasks such as pattern recognition, object identification or object tracking. The acquired knowledge is encoded in a form of individuals/learners which are able to process visual information. The originality of this approach lies also in the fact that individuals do not process raw image data directly. Instead, they operate on a set of attributed visual primitives that are acquired from images in the preliminary stage of the processing. The proposed approach is very general, because it uses the learning principle. For the purpose of learning we use genetic programming. Each individual/learner represents a procedure in a form of a tree of operations on sets of visual primitives. The images from the training set in our approach are not labeled in any way and no information is assigned with them. It means that the knowledge is acquired in totally unsupervised way. The only feedback information that states which individual better represents the target concept from the training set is the measure how the individual is able to reconstruct the input image. The rational standing behind this approach is following. We believe that a visual concept can be proved to be acquired and understood only if it can be reconstructed and successfully compared with original image from it was previously learned. In the thesis we present our methodology in details and describe its exemplary implementation that is based on the concept of segment as visual primitive. The method is verified on several sets of shapes of simple objects such as triangles, sections, Y letters and others. We also elaborate a methodology of cross-task knowledge sharing that is a step towards modularization of knowledge and provide results of massive experiments with cross-task knowledge sharing. Finally, the most important design decisions of software environment that was developed as a platform for computational experiments with our approach are described. A particular emphasis is put on computational performance issues of the developed software." @default.
• W150398843 created "2016-06-24" @default.
• W150398843 creator A5002205472 @default.
• W150398843 date "2006-01-01" @default.
• W150398843 modified "2023-09-26" @default.
• W150398843 title "GENETIC PROGRAMMING WITH CROSS-TASK KNOWLEDGE SHARING FOR LEARNING OF VISUAL CONCEPTS" @default.
• W150398843 cites W138562460 @default.
• W150398843 cites W1482827835 @default.
• W150398843 cites W1517016597 @default.
• W150398843 cites W1542723682 @default.
• W150398843 cites W1568906816 @default.
• W150398843 cites W1576818901 @default.
• W150398843 cites W1596794420 @default.
• W150398843 cites W1659842140 @default.
• W150398843 cites W2055289715 @default.
• W150398843 cites W2095752500 @default.
• W150398843 cites W2130355536 @default.
• W150398843 cites W2149228163 @default.
• W150398843 cites W2162473406 @default.
• W150398843 cites W2418011578 @default.
• W150398843 cites W2567075333 @default.
• W150398843 cites W2764433274 @default.
• W150398843 cites W3195079929 @default.
• W150398843 cites W609513197 @default.
• W150398843 cites W1496606080 @default.
• W150398843 hasPublicationYear "2006" @default.
• W150398843 type Work @default.
• W150398843 sameAs 150398843 @default.
• W150398843 citedByCount "1" @default.
• W150398843 crossrefType "journal-article" @default.
• W150398843 hasAuthorship W150398843A5002205472 @default.
• W150398843 hasConcept C110332635 @default.
• W150398843 hasConcept C111919701 @default.
• W150398843 hasConcept C119857082 @default.
• W150398843 hasConcept C145420912 @default.
• W150398843 hasConcept C154945302 @default.
• W150398843 hasConcept C177264268 @default.
• W150398843 hasConcept C199360897 @default.
• W150398843 hasConcept C2779321571 @default.
• W150398843 hasConcept C2779542340 @default.
• W150398843 hasConcept C2781238097 @default.
• W150398843 hasConcept C31972630 @default.
• W150398843 hasConcept C33923547 @default.
• W150398843 hasConcept C41008148 @default.
• W150398843 hasConcept C98045186 @default.
• W150398843 hasConceptScore W150398843C110332635 @default.
• W150398843 hasConceptScore W150398843C111919701 @default.
• W150398843 hasConceptScore W150398843C119857082 @default.
• W150398843 hasConceptScore W150398843C145420912 @default.
• W150398843 hasConceptScore W150398843C154945302 @default.
• W150398843 hasConceptScore W150398843C177264268 @default.
• W150398843 hasConceptScore W150398843C199360897 @default.
• W150398843 hasConceptScore W150398843C2779321571 @default.
• W150398843 hasConceptScore W150398843C2779542340 @default.
• W150398843 hasConceptScore W150398843C2781238097 @default.
• W150398843 hasConceptScore W150398843C31972630 @default.
• W150398843 hasConceptScore W150398843C33923547 @default.
• W150398843 hasConceptScore W150398843C41008148 @default.
• W150398843 hasConceptScore W150398843C98045186 @default.
• W150398843 hasLocation W1503988431 @default.
• W150398843 hasOpenAccess W150398843 @default.
• W150398843 hasPrimaryLocation W1503988431 @default.
• W150398843 hasRelatedWork W1555905994 @default.
• W150398843 hasRelatedWork W1596794420 @default.
• W150398843 hasRelatedWork W1981380486 @default.
• W150398843 hasRelatedWork W2002136732 @default.
• W150398843 hasRelatedWork W2014897236 @default.
• W150398843 hasRelatedWork W2030581694 @default.
• W150398843 hasRelatedWork W2049404817 @default.
• W150398843 hasRelatedWork W2129779498 @default.
• W150398843 hasRelatedWork W2141357123 @default.
• W150398843 hasRelatedWork W2142547660 @default.
• W150398843 hasRelatedWork W2162473406 @default.
• W150398843 hasRelatedWork W2167210612 @default.
• W150398843 hasRelatedWork W2240434391 @default.
• W150398843 hasRelatedWork W2784652921 @default.
• W150398843 hasRelatedWork W2786443043 @default.
• W150398843 hasRelatedWork W2979425476 @default.
• W150398843 hasRelatedWork W3017693819 @default.
• W150398843 hasRelatedWork W315826711 @default.
• W150398843 hasRelatedWork W3160886270 @default.
• W150398843 hasRelatedWork W817912545 @default.
• W150398843 isParatext "false" @default.
• W150398843 isRetracted "false" @default.
• W150398843 magId "150398843" @default.
• W150398843 workType "article" @default.