This study used hyperspectral imaging technique to detect grey mold disease on tomato leaves. Hyperspectral images of diseased samples at 24h, 48h, 72h, 96h and 120h after inoculation and healthy samples were taken in the wave range of 380-1023 nm. A total of ten pixels from each sample were identified as the region of interest (ROI), and the average reflectance values of ROI were calculated. The dependent variables of healthy samples were set as 0, and diseased samples were set as 1, 2, 3, 4 and 5 according to infection stages, respectively. K-nearest neighbor (KNN) model was built to classify the samples using the full wave band set. To reduce data volume, competitive adaptive reweighted sampling (CARS) was used to select sensitive bands. Then, the KNN model was built based on just the selected bands. This later procedure of reducing spectral dimensionality and classifying infection stages was defined as CARS-KNN. Performances of KNN classifier on all wave bands and CARS-KNN were compared. The overall classification results of the testing sets using all wave bands and KNN classifier were 59.72% and 65.28% for CARS-KNN. When differentiating infected samples from control ones, the results were 94.44% for KNN and 95.83% for CARS-KNN. In addition, early disease detection (1dpi) obtained the results of 66.67% in KNN and 75.00% in CARS-KNN. Therefore, it demonstrated that hyperspectral imaging has the potential to be used for early detection of grey mold disease on tomato leaves.