Cooking of potatoes causes changes in the microstructure and composition of starch. These changes affect the interaction of light with the starch granules at different regions inside the potato. In this research, the potential of hyperspectral imaging in combination with chemometric tools for contactless detection of the cooking front in potatoes has been investigated. Boiled potatoes cooked for 0 to 30 minutes were cut into halves and their cut surfaces were scanned by a hyperspectral camera in the wavelength range 400-1000 nm. Partial least squares discriminant analysis (PLSDA) was employed to discriminate between the pixel spectra for the cooked regions and those for the remaining raw regions. From each of the resulting images with detected cooking fronts, the relative area, which is the ratio of the remaining raw part area over the total potato area, was calculated. Then a heat transfer model was applied to plot the relative area against the cooking time and the optimal cooking time was defined as the time when the relative area became zero. It was found that the optimal cooking time could be precisely predicted by measuring one potato sample without cooking and another cooked for 12 to 21 minutes. The results illustrate the potential of hyperspectral imaging as a process monitoring tool for the potato processing industry.