Title :
Study on remote sensing image classification based on artificial immune system
Author_Institution :
Sch. of Urban & Environ. Sci., Huaiyin Normal Univ., Huai-an, China
Abstract :
On the base of analyzing the disadvantages of the negative selection algorithm, a bidirectional selection algorithm based on artificial immune system is presented. Clone selection and mutation algorithms are used on the training sample set to obtain mature antibody set. Then the mature antibody set can be used to classify the remote sensing image. It is demonstrated that this algorithm is superior to conventional maximum likelihood classification. Its accuracy reaches 87.4 percent.
Keywords :
artificial immune systems; biology computing; image classification; maximum likelihood estimation; remote sensing; artificial immune system; bidirectional selection algorithm; clone selection; mature antibody set; maximum likelihood classification; mutation algorithms; negative selection algorithm; remote sensing image classification; artificial immune system; image classification; negative selection; pattern recognition; remote sensing;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2011 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-8727-1
DOI :
10.1109/CSAE.2011.5952734
