Using Stochastic Grouping Strategy Based Fruit Fly Optimization to Perform the Template Matching

摘要

In this paper, an improved fruit fly optimization algorithm based on stochastic grouping strategy (SG-FFO) is put forward to perform the template matching. As a new bio-inspired optimization algorithm, fruit fly optimization (FFO) has a wide application prospect in many practical engineering. However, FFO has the defects of easily causing the phenomenon of premature convergence, which hampers its use in template matching. In our work, to overcome the insufficiency, a novel stochastic grouping strategy was integrated into the vision search phase of FFO, as well as the update rule in the olfactory search phase was also redefined. It is obvious that SG-FFO can effectively increase the diversity of population and enhance the global exploration ability when optimizing the six famous benchmark functions. Additionally, the comparison experimental results in solving template matching problems also demonstrate the superiority of our proposed algorithm in terms of the stability and efficiency over the other intelligence algorithms.