Abstract
For hyperspectral image processing, dimensionality reduction is an important step, which has direct impact on hyperspectral image classification accuracy. Unsupervised band selection is an important means of data dimensionality reduction. This paper presents an ant colony optimization (ACO) algorithm based hyperspectral image band selection method (ACO-BS). First, four kinds of distance are used to measure the difference between the bands so to turn the band selection problem into a cumulative distance optimization problem. In order to solve the band selection problem, an ant colony optimization algorithm procedure is given, including the path search criteria (transition probability) and exchange rules (pheromone update). Experiments show that regardless of the Maximum Likelihood (ML) or Support Vector Machine (SVM), the ACO-BS selected band can get higher classification accuracy, cosine distance has obvious advantages among the four kinds of distance, followed by mutual information.
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.
