Abstract
ABSTRACTThis paper proposes a hybrid algorithm for segmenting the layers and dark sand dune regions in Mars satellite images, using particle swarm optimization (PSO)-based adaptive K-means clustering with the level set model. These varieties of images are taken from the surface of Mars orbit. Because of the presence of layers and dark sand dune regions in these images, automatic segmentation of these images is very complex when identifying these regions. Segmentation of such images may lead to improper results with conventional level set. We propose a level set evolution based on the PSO with an adaptive K-means clustering algorithm for segmentation of these images. In adaptive K-means, there is no requirement to mention the number when clustering in advance as it generates consistent output. Using binary PSO, the “best” number of clusters is selected. The centres of the chosen clusters is refined via the adaptive K-means clustering to find a new “optimal” number of clusters automatically in the corresponding images to get a more precise clustering efficiency. This is achieved by PSO-based adaptive K-means clustered images which are hybridized with a new signed pressure function. This approach is successfully demonstrated on Mars satellite images, this experiments have shown superiority over previous techniques in terms of more robust, accurate and faster.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.