Citrus greening or Huanglongbing (HLB) is one of most serious citrus diseases in the world. Once a tree is infected, there is no cure. The feasibility was investigated for discriminating citrus greening by use of near infrared (NIR) spectroscopy and least square support vector machine (LS-SVM). The spectra of sound and citrus greening samples were recorded in the wavenumber range of 4000-9000 cm<sup>-1</sup>. The preprocessing method of second derivative with a gap of seven was adapted to eliminate spectral baseline. The spectral variables were optimized by principal component analysis (PCA) and (UVE) algorithms. The unknown samples were used to access the performance of the models. Compared to the PLS-DA model, the LS-SVM was better with the input vector of the first 15 principal components and linear kernel function. The regularization factor (γ) of linear kernel function was 1.8756, and the operation time of LS-SVM model was 0.86s. The recognition error of the LS-SVM model was zero. The results showed that the combination of LS-SVM and NIR spectroscopy could detect citrus greening nondestructively and rapidly.