A new bio-inspired method for remote sensing imagery classification
This work addresses satellite image classification, which is important for remote sensing applications, but appears incremental as it builds on existing neural network methods.
The paper tackles the problem of supervised classification of satellite imagery by grouping pixels into homogeneous regions, proposing a method that combines radial basis function clustering with a growing neural gas classifier to improve upon previous networks, with results demonstrated on numeric remote sensing imagery and applied to an image of Oran city in Algeria.
The problem of supervised classification of the satellite image is considered to be the task of grouping pixels into a number of homogeneous regions in space intensity. This paper proposes a novel approach that combines a radial basic function clustering network with a growing neural gas include utility factor classifier to yield improved solutions, obtained with previous networks. The double objective technique is first used to the development of a method to perform the satellite images classification, and finally, the implementation to address the issue of the number of nodes in the hidden layer of the classic Radial Basis functions network. Results demonstrating the effectiveness of the proposed technique are provided for numeric remote sensing imagery. Moreover, the remotely sensed image of Oran city in Algeria has been classified using the proposed technique to establish its utility.