Colour development of a product is often vital in the food industry. The study of the baking of biscuits reveals interesting colour development characteristic curves. Neural network methods are used to both represent and classify products according to these characteristics. Using self-organising maps well-defined characteristic curves are extracted. Colour data histogrammed along these curves are then accurately classified by feedforward neural networks trained by backpropagation. Image segmentation is implicit within this colour histogramming technique. The overall system has been shown to considerably outperform a human expert.
|Title of host publication||A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence|
|Publisher||World Scientific Publishing|
|Number of pages||7|
|Publication status||Published - 1995|
|Event||Australian Joint Conference on Artificial Intelligence (8th : 1995) - Canberra, Australia|
Duration: 13 Nov 1995 → 17 Nov 1995
|Conference||Australian Joint Conference on Artificial Intelligence (8th : 1995)|
|Period||13/11/95 → 17/11/95|
Raychaudhuri, T., Yeh, J., Hamey, L., Sung, S., & Westcott, T. (1995). A connectionist approach to quality assessment of food products. In X. Yao (Ed.), A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence (pp. 435-441). World Scientific Publishing.