An Optical fibre based sensor system has been developed for the purpose of examining the colour of food products online as they cook in a large-scale industrial oven. Spectroscopic techniques are employed to interrogate the sensor signal and the resultant output spectral patterns are examined by an Artificial Neural Network. A Pattern recognition system has, therefore, been developed which is capable of classifying colours that are favourable and those that are not optimum, in order to control the cooking process and optimise food quality.