Abstract: Non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ) works effectively in selecting bi-objective fea-tures，but may result in local convergence and prematurity in the process of optimization． In order to solve this problem，an improved NSGA-Ⅱ feature selection algorithm is proposed． In this algorithm，firstly，the first elite strategy is operated to select the elite population from parent population． Secondly，the selected parent elite popu-lation is combined with the offspring population to form a combined population． Finally，the second elite strategy is executed to obtain the next parent population． After the selection of 3D face expression candidate features，the selected features are classified by means of probabilistic neural network． Experimental results show that the pro-posed algorithm improves the performance of NSGA-Ⅱ with local convergence and prematurity problems greatly and increases the accuracy of facial expression recognition effectively．

Key words: non-dominated sorting genetic algorithm, feature selection, three-dimension model, expression re-cognition, probabilistic neural network