Abstract: In order to realize accurate and fast classification of potato, a novel detection method for potato external defects was proposed based on hyperspectral imaging technology. Potatoes with dry rot, normal and other six kinds of common defects were studied. First, region of interests spectral features of various defected areas were analyzed and principal component analysis method (PCA) was used to determined five characteristic bands (480、676、750、800 and 960 nm). Next, PCA was performed again based on characteristic bands and the second principal component was used to classify defects of potatoes, the overall classification success rate was only 61.52%. In order to improve classification success rate, band ratio algorithm and the symmetrical second difference algorithm were combined to detect external defects of potatoes. Finally, the overall classification success rate was increased to 95.65%. It is concluded that hyperspectral imaging technology can be used to effectively detect common external defects of potato.