Abstract: In order to cultivate students' ability of development and application practice, this paper designs an experimental case of strawberry distortion recognition based on multi-scale convolutional neural network for students to learn and practice on the computer. In order to improve the recognition ability of distorted strawberry images, the multi-scale convolutional neural network is studied in this paper, and a recognition algorithm of distorted strawberry images is implemented. The experimental results show that the proposed algorithm has accurate recognition ability for strawberry distorted images, and effectively reduces the influence of illumination and background. Through this experimental case, students' understanding of artificial intelligence knowledge is deepened, their interest in learning artificial intelligence direction is cultivated, and their ability to develop and apply artificial intelligence projects is improved.