Efficient implementation of several multilevel thresholding algorithms using a combinatorial scheme

In this study, we present a combinatorial scheme for reducing the computation timings of determining the optimal threshold values in multilevel thresholding. By applying the proposed scheme on criterion-based multilevel thresholding, not only do we effectively avoid the redundant evaluation of threshold sets, but we also substantially suppress the computation cost for each evaluation of each potential threshold set, thereby significantly reducing the computation timings for obtaining the optimal set of threshold values. In addition, this proposed scheme achieves the parameterization of the desired number of thresholds. We have implemented this scheme on multilevel thresholding using the criterion functions of three well-known methods: the between-class variance method, the maximum entropy method, and the minimum error method. Experimental results demonstrate the feasibility and computational efficiency of the proposed scheme on multilevel thresholding. Performance evaluations of these three criterion functions in multilevel thresholding are also presented in the experimental results.