Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/15963
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKeserwani P.-
dc.contributor.authorAli T.-
dc.contributor.authorPratim Roy, Partha-
dc.date.accessioned2020-12-02T11:42:07Z-
dc.date.available2020-12-02T11:42:07Z-
dc.date.issued2018-
dc.identifier.citationProceedings of 4th Asian Conference on Pattern Recognition, ACPR 2017, (2018), 292- 297-
dc.identifier.isbn9.78154E+12-
dc.identifier.urihttps://doi.org/10.1109/ACPR.2017.122-
dc.identifier.urihttp://repository.iitr.ac.in/handle/123456789/15963-
dc.description.abstractText region proposal is one of the fundamental tasks required for text detection and recognition in the natural images. This paper proposes a Convolutional Neural Network (CNN) based Text Region Proposal Network (TRPN) for generating word level region proposal. The proposed architecture is capable of getting trained on the low memory GPU and achieves a good recall with a limited number of region proposals to reduce the overhead on the detection and recognition task. The number of parameters of the proposed architecture is reduced to make it trainable on the low memory GPU by first decreasing the number of kernels and increasing them afterward. The in-network fusion is used to maintain localization accuracy which was reduced due to max-pooling operation. This fuses the feature map of different levels to obtain an efficient localization of text with different aspect ratio and size. The proposed architecture achieves a competitive recall with few tens of region proposals which are less compared to the state-of-The-Art region proposal methods for text. The results are validated on test-set of ICDAR 2013 and SVT datasets. © 2017 IEEE.-
dc.language.isoen_US-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.relation.ispartofProceedings of 4th Asian Conference on Pattern Recognition, ACPR 2017-
dc.subjectConvolutional Neural Network-
dc.subjectlow memory GPU-
dc.subjectregion proposal-
dc.titleTRPN: A text region proposal network in the wild under the constraint of low memory GPU-
dc.typeConference Paper-
dc.scopusid57205562856-
dc.scopusid55314607400-
dc.scopusid56880478500-
dc.affiliationKeserwani, P., Indian Institute of Technology Roorkee, Roorkee, Uttrakhand, India-
dc.affiliationAli, T., Indian Institute of Technology Roorkee, Roorkee, Uttrakhand, India-
dc.affiliationRoy, P.P., Indian Institute of Technology Roorkee, Roorkee, Uttrakhand, India-
dc.identifier.conferencedetails4th Asian Conference on Pattern Recognition, ACPR 2017, 26-29 November 2017-
Appears in Collections:Conference Publications [CS]

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


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