Improved CycleGAN-based feature recognition in young children and preschool education research

Pre-school education is an integral part of primary education, and with the development of digital technology, the integration of pre-school education and information technology development is deepening. The study first adds category constraints to the CycleGAN network to improve the efficiency of algorithm operations. The facial features of young children are extracted using the LBP method and recognized by improving the CycleGAN network after they are classified using the SOC classification method. On this basis, the improved model is applied to early childhood preschool education to explore the recognition of young children’s characteristics and educational effects. In this paper, the recognition accuracy of the improved CycleGAN network model is improved by 0.02~0.14 in the expression recognition accuracy of seven basic expressions. in early childhood education, the third round of test scores of the experimental group of young children is 93 compared to the first round of test improved by 34 points, compared with the control group scores improved by 15 points. This study provides practical and feasible development directions for constructing and reforming information technology in preschool education.