An improved feature set for hyperspectral image classification: harmonic analysis optimized by multiscale guided filter

HIGHLIGHTS

• who: Multiscale Guided Filter et al. from the extreme learning machine (ELM), are selected as the base classifiers for multiple EL in this articleThe RF is a statistical learning method by using the bootstrap resampling theory, which has been proven to have a high predictability accuracy and fine tolerance for outliers and noise [60], [61]. The RoF focuses on generating the rotation feature space by using PCA to improve feature diversity, and it performs a good performance on improving the classification results [62], [63]. The PSO-SVM is a powerful classifier in dealing with small-size training . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.