A data-driven meat freshness monitoring and evaluation method using rapid centroid estimation and hidden Markov models

•Introduce a powerful statistical tool, HMM, to the area of food quality control.•Propose a monitoring method based on a single HMM trained only by fresh samples.•Realize freshness evaluation according to the label given by the Viterbi algorithm.•Improve the training algorithm of HMM by proposing a Segmental-RCE algorithm.