In food industry, quality and safety are considered important issues worldwide that are directly related to health and social progress. The use of vision technology for quality testing of food production has the obvious advantage of being able to continuously monitor a production using non-destructive methods, thus increasing the quality and minimizing cost. The performance of an intelligent decision support system has been evaluated in monitoring the spoilage of minced beef stored either aerobically or under modified atmosphere packaging, at different storage temperatures (0, 5, 10, and 15 °C) utilising multispectral imaging information. This paper utilises a neuro-fuzzy model which incorporates a clustering pre-processing stage for the definition of fuzzy rules, while its final fuzzy rule base is determined by competitive learning. Initially, meat samples are classified according to their storage conditions, while identification models are then utilised for the prediction of the Total Viable Counts of bacteria. The innovation of the proposed approach is further extended to the identification of the temperature used for storage, utilizing only imaging spectral information. Results indicated that spectral information in combination with the proposed modelling scheme could be considered as an alternative methodology for the accurate evaluation of meat spoilage.