Choosing a suitable method for classifying the progressive colour fading of cured ham

Sliced ham products undergo significant discolouration and fading when placed retail display cabinets. This is due to factors such as illumination of display cabinet, packaging, i.e. low OTR (oxygen transmission rate) or very low OTR packaging, product to headspace ratio and percentage of residual oxygen. This paper presents initial investigations into the development of a sensor to measure rate of colour fading in cured ham, in order to predict an optimum colour sell-by-date. In particular, a comparison was made between a neural network trained using the back-propagation algorithm and a self-organising map (SOM) to identify which was more suitable for the purpose of classifying the data into five colour fading stages, from very pink to grey. The data set had a significant amount of overlapping between categories and results presented here show that the SOM could prove an effective system for determining the rate of colour fading in ham due to its topological feature preservation characteristic