Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372323218> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4372323218 abstract "Abstract Document Layout Analysis plays an important part in understanding the content of the document and extracting OCR text. Existing methods rely primarily on parallel analytical and identification techniques. Based on the analysis of the advantages and disadvantages of parallel methods, this article proposes a Serial Classification Recognition Method based on the improved architecture of the Mask R-CNN. To be specific, an improved feature pyramid model SCBAM-FPN is proposed, which utilizes Spatial Attention Module and Channel Attention Module as well as Atrous Convolution to reduce the loss of local information in feature maps and expand the receptive field, thereby increasing the performance of FPN express ability. Experiments show that using SCBAM-FPN to replace the original feature pyramid network in Mask R-CNN improves the detection performance of Mask R-CNN network for multi-scale targets. In addition, in order to improve the accuracy of segmentation, a Mask edge correction algorithm is proposed, which combines the FCN semantic segmentation results with edge superpixel information and uses the Mask-IoU mechanism to perform edge corrections on Masks with scores of less than 90%. The serial classification recognition method utilizes the improved Mask R-CNN architecture to perform Document Layout Analysis. Firstly, the document image is recognized and the table is segmented. Secondly, the image after the split table is used to identify and segment the illustrations. Finally, identify the title and paragraph of the image after removing the table and the illustration. Although the serial classification and recognition method has a certain degree of decline in speed, this method solves the problem of competition among multiple attributes and improves the accuracy of recognition compared with existing methods. In this article, experiments that were conducted on three datasets show that the proposed method surpasses existing methods in terms of accuracy and efficiency." @default.
- W4372323218 created "2023-05-07" @default.
- W4372323218 creator A5016584164 @default.
- W4372323218 creator A5016643749 @default.
- W4372323218 creator A5083414479 @default.
- W4372323218 date "2023-05-05" @default.
- W4372323218 modified "2023-10-16" @default.
- W4372323218 title "Serial Document Layout Analysis Method Based on Improved Mask R-CNN Architecture" @default.
- W4372323218 doi "https://doi.org/10.21203/rs.3.rs-2884489/v1" @default.
- W4372323218 hasPublicationYear "2023" @default.
- W4372323218 type Work @default.
- W4372323218 citedByCount "0" @default.
- W4372323218 crossrefType "posted-content" @default.
- W4372323218 hasAuthorship W4372323218A5016584164 @default.
- W4372323218 hasAuthorship W4372323218A5016643749 @default.
- W4372323218 hasAuthorship W4372323218A5083414479 @default.
- W4372323218 hasBestOaLocation W43723232181 @default.
- W4372323218 hasConcept C120665830 @default.
- W4372323218 hasConcept C121332964 @default.
- W4372323218 hasConcept C124101348 @default.
- W4372323218 hasConcept C138885662 @default.
- W4372323218 hasConcept C142575187 @default.
- W4372323218 hasConcept C153180895 @default.
- W4372323218 hasConcept C154945302 @default.
- W4372323218 hasConcept C162307627 @default.
- W4372323218 hasConcept C2776401178 @default.
- W4372323218 hasConcept C31972630 @default.
- W4372323218 hasConcept C41008148 @default.
- W4372323218 hasConcept C41895202 @default.
- W4372323218 hasConcept C45235069 @default.
- W4372323218 hasConcept C45347329 @default.
- W4372323218 hasConcept C50644808 @default.
- W4372323218 hasConcept C81363708 @default.
- W4372323218 hasConcept C89600930 @default.
- W4372323218 hasConceptScore W4372323218C120665830 @default.
- W4372323218 hasConceptScore W4372323218C121332964 @default.
- W4372323218 hasConceptScore W4372323218C124101348 @default.
- W4372323218 hasConceptScore W4372323218C138885662 @default.
- W4372323218 hasConceptScore W4372323218C142575187 @default.
- W4372323218 hasConceptScore W4372323218C153180895 @default.
- W4372323218 hasConceptScore W4372323218C154945302 @default.
- W4372323218 hasConceptScore W4372323218C162307627 @default.
- W4372323218 hasConceptScore W4372323218C2776401178 @default.
- W4372323218 hasConceptScore W4372323218C31972630 @default.
- W4372323218 hasConceptScore W4372323218C41008148 @default.
- W4372323218 hasConceptScore W4372323218C41895202 @default.
- W4372323218 hasConceptScore W4372323218C45235069 @default.
- W4372323218 hasConceptScore W4372323218C45347329 @default.
- W4372323218 hasConceptScore W4372323218C50644808 @default.
- W4372323218 hasConceptScore W4372323218C81363708 @default.
- W4372323218 hasConceptScore W4372323218C89600930 @default.
- W4372323218 hasLocation W43723232181 @default.
- W4372323218 hasOpenAccess W4372323218 @default.
- W4372323218 hasPrimaryLocation W43723232181 @default.
- W4372323218 hasRelatedWork W1669643531 @default.
- W4372323218 hasRelatedWork W2134924024 @default.
- W4372323218 hasRelatedWork W2295021132 @default.
- W4372323218 hasRelatedWork W2517104666 @default.
- W4372323218 hasRelatedWork W2760085659 @default.
- W4372323218 hasRelatedWork W2929240682 @default.
- W4372323218 hasRelatedWork W2969680539 @default.
- W4372323218 hasRelatedWork W3106036237 @default.
- W4372323218 hasRelatedWork W3136410232 @default.
- W4372323218 hasRelatedWork W3148519004 @default.
- W4372323218 isParatext "false" @default.
- W4372323218 isRetracted "false" @default.
- W4372323218 workType "article" @default.