Please use this identifier to cite or link to this item: http://gukir.inflibnet.ac.in:8080/jspui/handle/123456789/3789
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMukarambi G
dc.contributor.authorMallapa S
dc.contributor.authorDhandra B.V.
dc.date.accessioned2020-06-12T15:01:19Z-
dc.date.available2020-06-12T15:01:19Z-
dc.date.issued2017
dc.identifier.citationProceedings of 2017 3rd IEEE International Conference on Sensing, Signal Processing and Security, ICSSS 2017 , Vol. , , p. 214 - 217en_US
dc.identifier.uri10.1109/SSPS.2017.8071593
dc.identifier.urihttp://gukir.inflibnet.ac.in:8080/jspui/handle/123456789/3789-
dc.description.abstractIn this paper, an algorithm is proposed for Trilingual Script Identification System in block wise for camera captured images. The Local Binary Pattern (LBP) features are used for Kannada, Hindi and English images for testing the performance of a proposed algorithm, a dataset of 6000 neat block images are considered. For each script a total of 2000 images are used for the proposed method. The segmentation technique is used to segment the document image in blocks. Block of sizes 128×128, 256×256, 512×512 and 1024×1024 for Kannada, Hindi and English have been considered. The LBP features are extracted in 8 neighbors, there by generating 59 features and submitted to KNN and SVM classifiers to classify the underlying image. The identification accuracy for KNN and SVM classifiers are respectively 96.60% and 98.00% for block size 128×128, 98.71% and 98.07% for block size 256×256, 99.70% and 98.00% for block size 512×512 and further 94.90% and 99.01% for block size 1024×1024 respectively. The optimal accuracy is 99.01% for SVM classifier for block size 1024×1024. The proposed method is independent of thinning. © 2017 IEEE.en_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.subjectCamera Based Document image analysis
dc.subjectKNN
dc.subjectLBP
dc.subjectScript Identification
dc.subjectSVM
dc.titleScript identification from camera based Tri-Lingual documenten_US
dc.typeConference Paper
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.