O'Farrell, M; Lewis, E; Flanagan, C; Lyons, WB; Jackman, N

2005

December

Ieee Sensors Journal

Design of a system that uses optical-fiber sensors and neural networks to control a large-scale industrial oven by monitoring the food quality online

Published

()

artificial neural network (ANN) back propagation learning color classification feed forward networks food processing industry Karhunen-Loeve decomposition optical fiber sensor pattern recognition principal component analysis (PCA) spectral classification spectroscopy REFLECTANCE VISION COLOR CLASSIFICATION SPECTROSCOPY INSPECTION TISSUE APPLES PROBE BEEF

5

6

1407

1420

An optical-fiber sensor-based system has been designed to assist in the controlling of a large-scale industrial by monitoring the color of the food product being cooked. The system monitors the color of the food as it cooks by examining the reflected visible light, from the surface and/or core of the cooked product. A trained backpropogation neural network acts as a classifier and is used to interpret the extent to which each product is cooked with regard to the aesthetics of the food. Principal component analysis is also included before the neural network as a method of feature extraction. This is implemented using Karhunen-Loeve decomposition. A wide range of food products have been examined and accurately classified, demonstrating the versatility and repeatability of the system over time. These products include minced beef burgers and steamed chicken filets.

1530-437X

10.1109/JSEN.2005.858963