Abstract: In recent years, with the development of social media, image recognition has been widely used in the fields of video analysis, object detection and image retrieval. However, due to the complexity of data sources, there are differences in the distribution of data in different fields. To improve the recognition ability of cross-domain images, this paper proposes a projection reconstruction based domain-adaptive dictionary pair learning (PRDDPL) method. This method employs cross-reconstruction technique to construct new source and target domains, uses synthesis and analysis dictionary pairs to align samples in different domains, and utilizes the association of dictionary atoms with class information to transfer discriminative information from the source domain to the target domain. At the same time, the discriminative ability of the dictionary is improved by analyzing the dictionary constraints. By minimizing the linear classification error of each class of data and maximizing the difference between different classes, the discriminative ability of the sparse coefficients is improved through the classification discriminant of the source domain and target domain. Experiments on real social media datasets show that the proposed method outperforms the comparison methods in classification accuracy.