Adaptive edge enhancement in SAR images. Training on the data vs. training on simulated data

Dimou, A; Jager, G; Frangos, P

dc.contributor.author	Dimou, A	en
dc.contributor.author	Jager, G	en
dc.contributor.author	Frangos, P	en
dc.date.accessioned	2014-03-01T02:41:41Z
dc.date.available	2014-03-01T02:41:41Z
dc.date.issued	2001	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30597
dc.subject	Artificial Neural Network	en
dc.subject	Edge Detection	en
dc.subject	Edge Enhancement	en
dc.subject	Sar Image	en
dc.subject	Supervised Classification	en
dc.subject.other	Adaptive filtering	en
dc.subject.other	Color image processing	en
dc.subject.other	Computer simulation	en
dc.subject.other	Data reduction	en
dc.subject.other	Edge detection	en
dc.subject.other	Image segmentation	en
dc.subject.other	Neural networks	en
dc.subject.other	Speckle	en
dc.subject.other	Synthetic aperture radar	en
dc.subject.other	Adaptive edge enhancement	en
dc.subject.other	Training on simulated data	en
dc.subject.other	Training on the data	en
dc.subject.other	Image enhancement	en
dc.title	Adaptive edge enhancement in SAR images. Training on the data vs. training on simulated data	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2001.959061	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2001.959061	en
heal.publicationDate	2001	en
heal.abstract	Edge detection and edge enhancement in SAR images is, due to the speckle effect, not so easily achieved. Here we consider edge enhancement as classification problem, i.e. we segment an image in several edge classes and a no edge class. Thus supervised classification techniques become available. We proposed an artificial neural network approach and interpret the output as 'grade of being an edge pixel'. For training of the network we applied two training strategies: 1. Selection of training samples from the data in a supervised way and 2. Artificial creation of training samples based on speckle statistics using a speckle simulation algorithm. Both strategies are applied on a data set acquired by DLR's E-SAR in L-Band. The outputs of the edge enhancement process are compared among each other and with RoA edge detector.	en
heal.journalName	IEEE International Conference on Image Processing	en
dc.identifier.doi	10.1109/ICIP.2001.959061	en
dc.identifier.volume	1	en
dc.identifier.spage	493	en
dc.identifier.epage	496	en