A colorimetric sensor array capable of discriminating the spoilage
degree of fish during storage was developed. The array was
made from selected chemically responsive dyes printed on a
hydrophobic membrane. Digital images of the dye array before
and after exposure to the head-gas were recorded to measure color
change profiles as an indicator of fish freshness. The color change
profiles were analyzed using principal component analysis and
neural network for classification of the degree of spoilage. An overall
classification accuracy of 87.5% was achieved. Results suggest
that colorimetric sensor arrays are feasible for quality assurance/
control of fish. The technology may be also useful for other types
of food containing high protein content. Further research is needed
to improve the sensor array’s accuracy for predicting fish freshness.