Abstract:Manilensis is one of the major pests in China. A method for recognizing different ages of manilensis was presented based on Kmeans clustering and principal component analysis (PCA) with selected feature wavelength. The hyperspectral images in the range of 400~1000nm of manilensis back at differnet ages among adult, 5age, 4age and 3age were collected and the average spectral information of target region on manilensis back with the size of 15 pixel×15 pixel was extracted. A wavelength secleting method with combined PCA algorithm and Kmeans clustering (K-PCA) was proposed. The model for identifying manilensis ages was built by using Fisher algorithm and then compared with K-PCA algorithm and successive projections algorithm (SPA). The experiment results showed that the K-PCA algorithm needed fewer wavelengths but with the higher accuracy of 98.25%. The final feature wavelengths of K-PCA algorithm were 468nm, 555nm, 635nm, 710nm, 729nm, 750nm, 786nm and 899nm. The proposed method provides a certain technology support for manilensis monitoring and precention.