جهت دسترسی به کاربرگه ی زیر، از این لینک استفاده کنید. http://dl.pgu.ac.ir/handle/Hannan/82250
Title: DeepCut: object segmentation from bounding box annotations using convolutional neural networks
Keywords: Science & Technology;Technology;Life Sciences & Biomedicine;Computer Science, Interdisciplinary Applications;Engineering, Biomedical;Engineering, Electrical & Electronic;Imaging Science & Photographic Technology;Radiology, Nuclear Medicine & Medical Imaging;Computer Science;Engineering;Bounding box;convolutional neural networks;DeepCut;image segmentation;machine learning;weak annotations;GRAPH-CUT SEGMENTATION;FLOW SEGMENTATION;MRI;OPTIMIZATION;GRABCUT;cs.CV;cs.CV;Nuclear Medicine & Medical Imaging;08 Information And Computing Sciences;09 Engineering
Issue Date: 4-May-2017
9-Nov-2016
18-Oct-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Description: In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in our case bounding boxes. It extends the approach of the well-known GrabCut[1] method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naïve approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.
Other Identifiers: http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000396115800030&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
0278-0062
http://hdl.handle.net/10044/1/45459
https://dx.doi.org/10.1109/TMI.2016.2621185
RTJ5557761-1
PO :RTJ5557761-1
NS/A000025/1
Type Of Material: OTHER
Appears in Collections:Faculty of Engineering

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


تمامی کاربرگه ها در کتابخانه ی دیجیتال حنان به صورت کامل محافظت می شوند.