In the “Internet+” era, the smart classroom has emerged as a significant focal point in the research on educational informatization. This advancement represents a synergistic melding of novel technologies and academic practices. Accordingly, this study proposes a smart classroom teaching model tailored for accounting courses in higher education institutions. Within this framework, we have developed a specialized model to evaluate teaching efficacy in such environments. This evaluation model incorporates an enhanced version of the basic YOLOv5s model, which has been modified in three key areas to facilitate the detection of students’ facial expressions during lectures. Furthermore, to accommodate low-resolution images, the model integrates an advanced DRN-F face super-resolution reconstruction algorithm, thereby augmenting the accuracy of face recognition. This paper introduces a composite model for assessing the effectiveness of smart classroom teaching by amalgamating the two refined models. Comparative analysis with traditional manual recognition methods reveals that our model aligns more closely with the actual attentive responses of students when their faces are unobscured. A practical study on the teaching application further substantiates the efficacy of the smart classroom approach. Employing an independent sample t-test, the findings demonstrate a statistically significant difference in the post-test scores between the experimental and control groups, with a Sig. Value of 0.001 (p<0.05). This indicates that the learning achievements of students under the smart classroom model are significantly enhanced compared to those in conventional teaching settings.