Please use this identifier to cite or link to this item:
|Title:||Multilayer image inpainting approach based on neural networks||Authors:||Wang, Q.
|Issue Date:||2009||Citation:||Wang, Q.,Wang, Z.-X.,Chang, C.S.,Yang, T. (2009). Multilayer image inpainting approach based on neural networks. 5th International Conference on Natural Computation, ICNC 2009 3 : 459-462. ScholarBank@NUS Repository. https://doi.org/10.1109/ICNC.2009.127||Abstract:||This paper describes an image inpainting approach based on the self-organizing map for dividing an image into several layers, assigning each damaged pixel to one layer, and then restoring these damaged pixels by the information of their respective layer. These inpainted layers are then fused together to provide the final inpainting results. This approach takes advantage of the neural network's ability of imitating human's brain to separate objects of an image into different layers for inpainting. The approach is promising as clearly demonstrated by the results in this paper. © 2009 IEEE.||Source Title:||5th International Conference on Natural Computation, ICNC 2009||URI:||http://scholarbank.nus.edu.sg/handle/10635/71042||ISBN:||9780769537368||DOI:||10.1109/ICNC.2009.127|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Aug 4, 2020
checked on Aug 2, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.