Matches in SemOpenAlex for { <https://semopenalex.org/work/W2068705048> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2068705048 abstract "Object detection and recognition still pose a major challenge for computer vision systems. The Viola-Jones framework is a popular means of building classifiers that can perform these tasks effectively and efficiently. Viola-Jones draws upon a set of simple, Haar-like image features at all scales and positions. As this set grows rapidly with image size, it can become costly to evaluate and also encourages overfitting of the classifier. Our paper presents a unique application of artificial evolution to pre-select features for use by the Viola-Jones training method. A population of classifiers is evolved with varying feature sets and tested on detecting human faces in images. Several search strategies are compared and a greedy approach is found to most reliably lead to classifiers with improved accuracy. Training time is particularly reduced by the use of smaller feature sets. However, the computational cost for evolving the sets is high and arguably only worthwhile if the set is to be reused to train further cascades, such as in a dynamically updated system." @default.
- W2068705048 created "2016-06-24" @default.
- W2068705048 creator A5085737719 @default.
- W2068705048 creator A5086953764 @default.
- W2068705048 creator A5089357579 @default.
- W2068705048 date "2012-05-01" @default.
- W2068705048 modified "2023-09-26" @default.
- W2068705048 title "Evolutionary Feature Preselection for Viola-Jones Classifier Training" @default.
- W2068705048 cites W1576660662 @default.
- W2068705048 cites W1988790447 @default.
- W2068705048 cites W2004088465 @default.
- W2068705048 cites W2017337590 @default.
- W2068705048 cites W2033419168 @default.
- W2068705048 cites W2107634464 @default.
- W2068705048 cites W3097096317 @default.
- W2068705048 cites W1932152151 @default.
- W2068705048 doi "https://doi.org/10.1109/scet.2012.6342142" @default.
- W2068705048 hasPublicationYear "2012" @default.
- W2068705048 type Work @default.
- W2068705048 sameAs 2068705048 @default.
- W2068705048 citedByCount "6" @default.
- W2068705048 countsByYear W20687050482016 @default.
- W2068705048 countsByYear W20687050482017 @default.
- W2068705048 countsByYear W20687050482020 @default.
- W2068705048 crossrefType "proceedings-article" @default.
- W2068705048 hasAuthorship W2068705048A5085737719 @default.
- W2068705048 hasAuthorship W2068705048A5086953764 @default.
- W2068705048 hasAuthorship W2068705048A5089357579 @default.
- W2068705048 hasConcept C106135958 @default.
- W2068705048 hasConcept C119857082 @default.
- W2068705048 hasConcept C123134398 @default.
- W2068705048 hasConcept C153180895 @default.
- W2068705048 hasConcept C154945302 @default.
- W2068705048 hasConcept C182521987 @default.
- W2068705048 hasConcept C22019652 @default.
- W2068705048 hasConcept C2776151529 @default.
- W2068705048 hasConcept C31510193 @default.
- W2068705048 hasConcept C40651066 @default.
- W2068705048 hasConcept C41008148 @default.
- W2068705048 hasConcept C4641261 @default.
- W2068705048 hasConcept C50644808 @default.
- W2068705048 hasConcept C51632099 @default.
- W2068705048 hasConcept C52622490 @default.
- W2068705048 hasConcept C95623464 @default.
- W2068705048 hasConceptScore W2068705048C106135958 @default.
- W2068705048 hasConceptScore W2068705048C119857082 @default.
- W2068705048 hasConceptScore W2068705048C123134398 @default.
- W2068705048 hasConceptScore W2068705048C153180895 @default.
- W2068705048 hasConceptScore W2068705048C154945302 @default.
- W2068705048 hasConceptScore W2068705048C182521987 @default.
- W2068705048 hasConceptScore W2068705048C22019652 @default.
- W2068705048 hasConceptScore W2068705048C2776151529 @default.
- W2068705048 hasConceptScore W2068705048C31510193 @default.
- W2068705048 hasConceptScore W2068705048C40651066 @default.
- W2068705048 hasConceptScore W2068705048C41008148 @default.
- W2068705048 hasConceptScore W2068705048C4641261 @default.
- W2068705048 hasConceptScore W2068705048C50644808 @default.
- W2068705048 hasConceptScore W2068705048C51632099 @default.
- W2068705048 hasConceptScore W2068705048C52622490 @default.
- W2068705048 hasConceptScore W2068705048C95623464 @default.
- W2068705048 hasLocation W20687050481 @default.
- W2068705048 hasOpenAccess W2068705048 @default.
- W2068705048 hasPrimaryLocation W20687050481 @default.
- W2068705048 hasRelatedWork W1487139558 @default.
- W2068705048 hasRelatedWork W1489207701 @default.
- W2068705048 hasRelatedWork W1920283106 @default.
- W2068705048 hasRelatedWork W2018273017 @default.
- W2068705048 hasRelatedWork W2052166365 @default.
- W2068705048 hasRelatedWork W2118399788 @default.
- W2068705048 hasRelatedWork W2124426566 @default.
- W2068705048 hasRelatedWork W2160360539 @default.
- W2068705048 hasRelatedWork W2164490983 @default.
- W2068705048 hasRelatedWork W2166222296 @default.
- W2068705048 hasRelatedWork W2170608400 @default.
- W2068705048 hasRelatedWork W2171188998 @default.
- W2068705048 hasRelatedWork W2291140369 @default.
- W2068705048 hasRelatedWork W2321691871 @default.
- W2068705048 hasRelatedWork W2345202531 @default.
- W2068705048 hasRelatedWork W2413412388 @default.
- W2068705048 hasRelatedWork W2534567134 @default.
- W2068705048 hasRelatedWork W2560269647 @default.
- W2068705048 hasRelatedWork W2622102053 @default.
- W2068705048 hasRelatedWork W2789506732 @default.
- W2068705048 isParatext "false" @default.
- W2068705048 isRetracted "false" @default.
- W2068705048 magId "2068705048" @default.
- W2068705048 workType "article" @default.