Abstract | ||
---|---|---|
Most studies have been based on the original computation mode of semivariogram and discrete semivariance values. In this paper, a set of texture features are described to improve the accuracy of object-oriented classification in remotely sensed images. So, we proposed a classification method support vector machine (SVM) with spectral information and texture features (ST-SVM), which incorporates texture features in remotely sensed images into SVM. Using kernel methods, the spectral information and texture features are jointly used for the classification by a SVM formulation. Then, the texture features were calculated based on segmented block matrix image objects using the panchromatic band. A comparison of classification results on real-world data sets demonstrates that the texture features in this paper are useful supplement information for the spectral object-oriented classification, and proposed ST-SVM classification accuracy than the traditional SVM method with only spectral information. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s00521-015-1862-7 | Neural Computing and Applications |
Keywords | Field | DocType |
SVM, ST-SVM, Kernel method, Remotely sensed images classification | Semivariance,Data set,Artificial intelligence,Computation,Kernel (linear algebra),Computer vision,Pattern recognition,Panchromatic film,Support vector machine,Kernel method,Machine learning,Block matrix,Mathematics | Journal |
Volume | Issue | ISSN |
27 | 2 | 1433-3058 |
Citations | PageRank | References |
10 | 0.53 | 28 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jian-qiang Gao | 1 | 61 | 5.12 |
Xu Lizhong | 2 | 155 | 24.51 |
Fengchen Huang | 3 | 28 | 4.21 |