Matches in SemOpenAlex for { <https://semopenalex.org/work/W6901147> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W6901147 abstract "For a document class, one challenge in document restoration is to automatically find a set of filters, which are adapted to the degradation level of the images. Furthermore, it is important to know what filters and where they can be applied advantageously. In this paper, we present a multi classifiers solution for the extraction of linear filters. These filters are used for binarization and image denoising. The technique starts by clustering close pixels by K-means in as many clusters as filters. Each cluster is dedicated to a filter, which corresponds to a supervised neural network. These classifiers are trained according to a binarized image that is weighted function to erosion transformation effects. The presented method is compared to classical binarization techniques in literature. Its effect on the commercial OCR performances reaches a gain from 0,16% for Finereader7 and 1,06% for Omnipage14 for the recognition rate." @default.
- W6901147 created "2016-06-24" @default.
- W6901147 creator A5002810227 @default.
- W6901147 creator A5025447862 @default.
- W6901147 date "2008-12-07" @default.
- W6901147 modified "2023-09-23" @default.
- W6901147 title "Dynamic filters selection for textual document images denoising" @default.
- W6901147 cites W1548783560 @default.
- W6901147 cites W1967238710 @default.
- W6901147 cites W1979615985 @default.
- W6901147 cites W1987236180 @default.
- W6901147 cites W2051084846 @default.
- W6901147 cites W2096832794 @default.
- W6901147 cites W2133059825 @default.
- W6901147 hasPublicationYear "2008" @default.
- W6901147 type Work @default.
- W6901147 sameAs 6901147 @default.
- W6901147 citedByCount "0" @default.
- W6901147 crossrefType "proceedings-article" @default.
- W6901147 hasAuthorship W6901147A5002810227 @default.
- W6901147 hasAuthorship W6901147A5025447862 @default.
- W6901147 hasConcept C104317684 @default.
- W6901147 hasConcept C106131492 @default.
- W6901147 hasConcept C106430172 @default.
- W6901147 hasConcept C115961682 @default.
- W6901147 hasConcept C153180895 @default.
- W6901147 hasConcept C154945302 @default.
- W6901147 hasConcept C160633673 @default.
- W6901147 hasConcept C163294075 @default.
- W6901147 hasConcept C177264268 @default.
- W6901147 hasConcept C185592680 @default.
- W6901147 hasConcept C199360897 @default.
- W6901147 hasConcept C204241405 @default.
- W6901147 hasConcept C31972630 @default.
- W6901147 hasConcept C41008148 @default.
- W6901147 hasConcept C52622490 @default.
- W6901147 hasConcept C55493867 @default.
- W6901147 hasConcept C73555534 @default.
- W6901147 hasConcept C9417928 @default.
- W6901147 hasConceptScore W6901147C104317684 @default.
- W6901147 hasConceptScore W6901147C106131492 @default.
- W6901147 hasConceptScore W6901147C106430172 @default.
- W6901147 hasConceptScore W6901147C115961682 @default.
- W6901147 hasConceptScore W6901147C153180895 @default.
- W6901147 hasConceptScore W6901147C154945302 @default.
- W6901147 hasConceptScore W6901147C160633673 @default.
- W6901147 hasConceptScore W6901147C163294075 @default.
- W6901147 hasConceptScore W6901147C177264268 @default.
- W6901147 hasConceptScore W6901147C185592680 @default.
- W6901147 hasConceptScore W6901147C199360897 @default.
- W6901147 hasConceptScore W6901147C204241405 @default.
- W6901147 hasConceptScore W6901147C31972630 @default.
- W6901147 hasConceptScore W6901147C41008148 @default.
- W6901147 hasConceptScore W6901147C52622490 @default.
- W6901147 hasConceptScore W6901147C55493867 @default.
- W6901147 hasConceptScore W6901147C73555534 @default.
- W6901147 hasConceptScore W6901147C9417928 @default.
- W6901147 hasOpenAccess W6901147 @default.
- W6901147 hasRelatedWork W2071507513 @default.
- W6901147 hasRelatedWork W2124830270 @default.
- W6901147 hasRelatedWork W2183012051 @default.
- W6901147 hasRelatedWork W2331814015 @default.
- W6901147 hasRelatedWork W2566298967 @default.
- W6901147 hasRelatedWork W2765127530 @default.
- W6901147 hasRelatedWork W2889064910 @default.
- W6901147 hasRelatedWork W2911064732 @default.
- W6901147 hasRelatedWork W2912710081 @default.
- W6901147 hasRelatedWork W2914145455 @default.
- W6901147 hasRelatedWork W2967839572 @default.
- W6901147 hasRelatedWork W2988678710 @default.
- W6901147 hasRelatedWork W2999985175 @default.
- W6901147 hasRelatedWork W3011971048 @default.
- W6901147 hasRelatedWork W3099012953 @default.
- W6901147 hasRelatedWork W3119522598 @default.
- W6901147 hasRelatedWork W3135835853 @default.
- W6901147 hasRelatedWork W3157156645 @default.
- W6901147 hasRelatedWork W3198662899 @default.
- W6901147 hasRelatedWork W3203430088 @default.
- W6901147 isParatext "false" @default.
- W6901147 isRetracted "false" @default.
- W6901147 magId "6901147" @default.
- W6901147 workType "article" @default.