Abstract
A two steps segmentation algorithm is presented, which is useful for the analysis of remote sensed images. According to a decision tree scheme the image is firstly, partitioned into topographical regions on the basis of a special region model; then the regions are classified by per-field classification methods using the most relevant features. Syntactic and statistic relations are used in the definition of region and edge: from them derives the image partitioning model. The corresponding segmentation algorithm results to have small sensitivity to noise and to small variations of the mean values of the features in each regions. A trade-off between enhancement and smoothness of the image can be made by proper tuning of the parameters. The numerical implementation of the algorithm does not involve great computational cost, considering that the algorithm is sequential and that it is suitable for a large range of images. Some numerical applications are reported.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
