ResearchSpace

Deep convolutional neural networks for dense non-uniform motion deblurring

Show simple item record

dc.contributor.author Cronje, J
dc.date.accessioned 2016-09-07T10:52:32Z
dc.date.available 2016-09-07T10:52:32Z
dc.date.issued 2015-11
dc.identifier.citation Cronje, J. 2015. Deep convolutional neural networks for dense non-uniform motion deblurring. In: The 30th International Conference on Image and Vision Computing New Zealand (IVCNZ 2015) , 23th - 24th November, Auckland, New Zealand en_US
dc.identifier.isbn 978-1-5090-0357-0
dc.identifier.uri http://hdl.handle.net/10204/8753
dc.description The 30th International Conference on Image and Vision Computing New Zealand (IVCNZ 2015), 23-24 November, Auckland, New Zealand. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website en_US
dc.description.abstract The work in this paper address the problem of removing non-uniform motion blur from a single image. The motion vector for an image patch is estimated by using a convolutional neural network (CNN). All the predicted motion vectors are combined to form a dense non-uniform motion estimation map. Furthermore, a second CNN is trained to perform deblurring given a blurry image patch and the estimated motion vector. Combining the two trained networks result in a deep learning approach that can enhance degraded images. The results show that this approach can accurately determine non-uniform motion blur and restore blurred images. en_US
dc.language.iso en en_US
dc.publisher IVCNZ 2015 Image and Vision Computing en_US
dc.relation.ispartofseries Workflow;16176
dc.subject Convolutional neural networks en_US
dc.subject CNN en_US
dc.subject Blurred images en_US
dc.subject Motion vector estimation en_US
dc.subject Image enhancements en_US
dc.subject Pattern recognition en_US
dc.title Deep convolutional neural networks for dense non-uniform motion deblurring en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Cronje, J. (2015). Deep convolutional neural networks for dense non-uniform motion deblurring. IVCNZ 2015 Image and Vision Computing. http://hdl.handle.net/10204/8753 en_ZA
dc.identifier.chicagocitation Cronje, J. "Deep convolutional neural networks for dense non-uniform motion deblurring." (2015): http://hdl.handle.net/10204/8753 en_ZA
dc.identifier.vancouvercitation Cronje J, Deep convolutional neural networks for dense non-uniform motion deblurring; IVCNZ 2015 Image and Vision Computing; 2015. http://hdl.handle.net/10204/8753 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Cronje, J AB - The work in this paper address the problem of removing non-uniform motion blur from a single image. The motion vector for an image patch is estimated by using a convolutional neural network (CNN). All the predicted motion vectors are combined to form a dense non-uniform motion estimation map. Furthermore, a second CNN is trained to perform deblurring given a blurry image patch and the estimated motion vector. Combining the two trained networks result in a deep learning approach that can enhance degraded images. The results show that this approach can accurately determine non-uniform motion blur and restore blurred images. DA - 2015-11 DB - ResearchSpace DP - CSIR KW - Convolutional neural networks KW - CNN KW - Blurred images KW - Motion vector estimation KW - Image enhancements KW - Pattern recognition LK - https://researchspace.csir.co.za PY - 2015 SM - 978-1-5090-0357-0 T1 - Deep convolutional neural networks for dense non-uniform motion deblurring TI - Deep convolutional neural networks for dense non-uniform motion deblurring UR - http://hdl.handle.net/10204/8753 ER - en_ZA


Files in this item

Thumbnail
Name: Cronje_2015_ABSTR ...
Size: 6.761Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record