Please use this identifier to cite or link to this item: https://idr.l2.nitk.ac.in/jspui/handle/123456789/8241
Full metadata record
DC FieldValueLanguage
dc.contributor.authorNaik, D.
dc.contributor.authorJaidhar, C.D.
dc.date.accessioned2020-03-30T10:18:15Z-
dc.date.available2020-03-30T10:18:15Z-
dc.date.issued2016
dc.identifier.citation11th International Conference on Industrial and Information Systems, ICIIS 2016 - Conference Proceedings, 2016, Vol.2018-January, , pp.724-729en_US
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/8241-
dc.description.abstractAn Encoder-Decoder Neural Network Architecture is combined with a novel strategy to improve global label consistency, to come with an improved image segmentation model. Label Distribution predictions extracted from the SegNet Network is investigated and used in the project for image labeling. An algorithm called Region Consistency Activation (RCA) to improve the global label consistency is implemented. RCA is based on a novel transformation between Ultra metric Contour Map (UCM) and the Probability of Regions Consistency (PRC). These algorithms were rigorously tested on the CamVid dataset. Superior performances were achieved compared with the state-of-the-art methods on this dataset. � 2016 IEEE.en_US
dc.titleImage segmentation using encoder-decoder architecture and region consistency activationen_US
dc.typeBook chapteren_US
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.