FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2600510418> ?p ?o ?g. }

• W2600510418 abstract "The automatic analysis and retrieval of technical line drawings is hindered by many challenges such as: the large amount of contextual clutter around the symbols within the drawings, degradation, transformations on the symbols in drawings, large databases of drawingsand large alphabets of symbols. The core tasks required for the analysis of technical linedrawings are: symbol recognition, spotting and retrieval. The current systems for performing these tasks have poor performance due to the mentioned challenges. This dissertationpresents a number of methods that address these challenges. These methods achieve bothaccurate and efficient symbol spotting and retrieval in technical line drawings, and performsignificantly better than state-of-the-art methods on the same problems. An overview ofthe key contributions of this dissertation is given in the following.First, this dissertation presents a geometric matching-based method for symbol recognitionand spotting. The method performs recognition in the presence of large amounts of contextual clutter, and provides precise localization of the recognized symbols. On standarddatabases such as GREC-2005 and GREC-2011, the method achieves up to 10% higherrecall and up to 28% higher precision than state-of-the-art methods on the spotting task,and achieves up to 7% higher recognition accuracy on the isolated recognition task. Themethod is based on a geometric matching approach, which is flexible enough to incorporateimprovements on the matching strategy, feature types and information on the features. Themethod also includes an adaptive preprocessing algorithm that deals with a wide varietyof noise types.In order to improve the performance of the spotting method when dealing with degradeddrawings, two novel methods are presented in this dissertation. Both methods are based oncombining geometric matching with machine learning techniques. The geometric matchingis used to automatically generate training data that contain information on how well thefeatures of the queries are matched in both the true and the false matches found by thespotting method. The first method learns the feature weights of the different query symbolsby linear discriminant analysis (LDA). The weighted query features are used in the spottingmethod and result in 27% higher average precision than the original method, with a speedupfactor of 2. The second method uses SVM classification as a post-spotting step to distinguishthe true from the false matches in the spotting method. The use of the classification stepfurther improves the average precision of the spotting method by 20.6%.This dissertation also presents methods for content analysis of line drawings. First, amethod for accurate and consistent detection (95.8%) of regions of interest (ROIs) is presented. The method is based on statistical feature grouping. The ROI-finding method isidentified as an important part of a symbol retrieval system: the better the detected ROIs,the higher the performance of a retrieval system. The ROI-finding method is also used toimprove the performance of the geometric-based spotting system.Second, a symbol clustering method for building a compact and accurate representation ofa large database of technical drawings is presented. This method uses the output from theROI-finding method as input, and uses geometric matching as a similarity measure. Themethod achieves high accuracy (90.1% recall, 94.3% precision) in forming clusters of symbols. The representatives of the clusters (34 symbols) are used as key entries to a symbolindex, which is identified as the outcome of an off-line stage of a symbol retrieval system.Finally, an efficient and high performing large scale symbol retrieval system is presentedin this dissertation. The system follows the bag of visual words (BoVW) model, but withusing methods that are suitable to line drawings. The system uses the symbol index torepresent a database of drawings. During the on-line query retrieval stage, the query isanalyzed by the ROI-finding method, matched with the key entries of the symbol index viageometric matching, and finally, a spatial verification step is performed on the retrievedmatches. The system achieves a query lookup time that is independent of the size of thedatabase, and is instead dependent on the size of the symbol index. The system achieves upto 10% higher recall and up to 28% higher precision than state-of-the-art spotting systemson similar databases.Overall, these contributions are major advancements in the research of graphics recognition.The hope is that, such contributions provide the basis for the development of reliable andaccurate performing applications for browsing, querying or classification of line drawingsfor the benefit of end users." @default.
• W2600510418 created "2017-04-07" @default.
• W2600510418 creator A5071877496 @default.
• W2600510418 date "2013-01-01" @default.
• W2600510418 modified "2023-09-26" @default.
• W2600510418 title "Geometric-based Symbol Spotting and Retrieval in Technical Line Drawings" @default.
• W2600510418 hasPublicationYear "2013" @default.
• W2600510418 type Work @default.
• W2600510418 sameAs 2600510418 @default.
• W2600510418 citedByCount "1" @default.
• W2600510418 countsByYear W26005104182018 @default.
• W2600510418 crossrefType "journal-article" @default.
• W2600510418 hasAuthorship W2600510418A5071877496 @default.
• W2600510418 hasConcept C105795698 @default.
• W2600510418 hasConcept C115961682 @default.
• W2600510418 hasConcept C132094186 @default.
• W2600510418 hasConcept C134400042 @default.
• W2600510418 hasConcept C138885662 @default.
• W2600510418 hasConcept C153180895 @default.
• W2600510418 hasConcept C154945302 @default.
• W2600510418 hasConcept C162324750 @default.
• W2600510418 hasConcept C165064840 @default.
• W2600510418 hasConcept C187736073 @default.
• W2600510418 hasConcept C199360897 @default.
• W2600510418 hasConcept C26517878 @default.
• W2600510418 hasConcept C2776401178 @default.
• W2600510418 hasConcept C2779506182 @default.
• W2600510418 hasConcept C2780451532 @default.
• W2600510418 hasConcept C31972630 @default.
• W2600510418 hasConcept C33923547 @default.
• W2600510418 hasConcept C34736171 @default.
• W2600510418 hasConcept C38652104 @default.
• W2600510418 hasConcept C41008148 @default.
• W2600510418 hasConcept C41895202 @default.
• W2600510418 hasConcept C554190296 @default.
• W2600510418 hasConcept C76155785 @default.
• W2600510418 hasConcept C99498987 @default.
• W2600510418 hasConceptScore W2600510418C105795698 @default.
• W2600510418 hasConceptScore W2600510418C115961682 @default.
• W2600510418 hasConceptScore W2600510418C132094186 @default.
• W2600510418 hasConceptScore W2600510418C134400042 @default.
• W2600510418 hasConceptScore W2600510418C138885662 @default.
• W2600510418 hasConceptScore W2600510418C153180895 @default.
• W2600510418 hasConceptScore W2600510418C154945302 @default.
• W2600510418 hasConceptScore W2600510418C162324750 @default.
• W2600510418 hasConceptScore W2600510418C165064840 @default.
• W2600510418 hasConceptScore W2600510418C187736073 @default.
• W2600510418 hasConceptScore W2600510418C199360897 @default.
• W2600510418 hasConceptScore W2600510418C26517878 @default.
• W2600510418 hasConceptScore W2600510418C2776401178 @default.
• W2600510418 hasConceptScore W2600510418C2779506182 @default.
• W2600510418 hasConceptScore W2600510418C2780451532 @default.
• W2600510418 hasConceptScore W2600510418C31972630 @default.
• W2600510418 hasConceptScore W2600510418C33923547 @default.
• W2600510418 hasConceptScore W2600510418C34736171 @default.
• W2600510418 hasConceptScore W2600510418C38652104 @default.
• W2600510418 hasConceptScore W2600510418C41008148 @default.
• W2600510418 hasConceptScore W2600510418C41895202 @default.
• W2600510418 hasConceptScore W2600510418C554190296 @default.
• W2600510418 hasConceptScore W2600510418C76155785 @default.
• W2600510418 hasConceptScore W2600510418C99498987 @default.
• W2600510418 hasLocation W26005104181 @default.
• W2600510418 hasOpenAccess W2600510418 @default.
• W2600510418 hasPrimaryLocation W26005104181 @default.
• W2600510418 hasRelatedWork W1831235333 @default.
• W2600510418 hasRelatedWork W2032159880 @default.
• W2600510418 hasRelatedWork W2052805987 @default.
• W2600510418 hasRelatedWork W2074489476 @default.
• W2600510418 hasRelatedWork W2093588204 @default.
• W2600510418 hasRelatedWork W2104737037 @default.
• W2600510418 hasRelatedWork W2154705238 @default.
• W2600510418 hasRelatedWork W2213387816 @default.
• W2600510418 hasRelatedWork W2333591360 @default.
• W2600510418 hasRelatedWork W2549132050 @default.
• W2600510418 hasRelatedWork W2559612992 @default.
• W2600510418 hasRelatedWork W2562989287 @default.
• W2600510418 hasRelatedWork W2786476081 @default.
• W2600510418 hasRelatedWork W2808077099 @default.
• W2600510418 hasRelatedWork W2885260042 @default.
• W2600510418 hasRelatedWork W289654536 @default.
• W2600510418 hasRelatedWork W2971240746 @default.
• W2600510418 hasRelatedWork W3034671543 @default.
• W2600510418 hasRelatedWork W3039706108 @default.
• W2600510418 hasRelatedWork W3110781124 @default.
• W2600510418 isParatext "false" @default.
• W2600510418 isRetracted "false" @default.
• W2600510418 magId "2600510418" @default.
• W2600510418 workType "article" @default.