Abstract
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. By classifying the measured colours it is possible to automatically determine if the food is cooked to an optimum perceived colour. Developments have been made on previous work by the authors by further examining the internal colour of the food and also looking at food that does not have an even colour externally. Spectroscopic techniques are employed to determine the colour and this signal is interrogated using an Artificial Neural Network. The resultant output spectral patterns can therefore be quantitatively classified and thus categorized.
Original language | English |
---|---|
Pages | 368-371 |
Number of pages | 4 |
Publication status | Published - 2003 |
Event | Second International Conference on Sensors: IEEE Sensors 2003 - Toronto, Ont., Canada Duration: 22 Oct 2003 → 24 Oct 2003 |
Conference
Conference | Second International Conference on Sensors: IEEE Sensors 2003 |
---|---|
Country/Territory | Canada |
City | Toronto, Ont. |
Period | 22/10/03 → 24/10/03 |
Keywords
- Artificial Neural Network
- Back Propagation Learning
- Colour Classification
- Feed Forward Networks
- Food Processing Industry
- Optical Fibre Sensor
- Pattern Recognition