Research on the Forecast Model of Total Viable Count on Bacon Based on Hyper spectral Imaging Technique

The total viable count (TVC) in bacon overweight can cause serious damage to human health. In order to find a rapid and nondestructive method of TVC, hyper spectral imaging technique was applied to quantitatively analysis of TVC on bacon. Comprehensively comparing the pretreatment method of multiple scattering, derivative method and so on, finally the multiple scattering for pretreatment was used. And the interval optimization method of least squares model was set up to predict, and get a good prediction results. The correlation coefficient of the calibration and predictions respectively was 0.808 and 0.808, interactive authentication root mean square error was 0.115 and 0.198 respectively. Therefore, hyper spectral imaging technique combining iPLS can be used for the rapid detection of TVC on bacon.