**5. Conclusions**

In this work, we presented a super-resolution method using Multilabel Gene Expression Programming. This method uses MGEP to extract a subset of image samples related to color and texture features in advance, and then performs nonlinear mapping and image reconstruction, thereby reducing the complexity of the convolutional neural network parameters so as to avoid the SR problems of slow training convergence and unstable recovery results. It was experimentally verified that the image restoration effect of this method under different magnifications and on training sets is better than that of the commonly used deep learning algorithms, and it also performs well in terms of subjective visual effects.

**Author Contributions:** Conceptualization, J.T.; methodology, C.H.; software, J.L.; validation, H.Z.; formal analysis, J.T.; investigation, C.H.; resources, J.L.; data curation, J.L.; writing—original draft preparation, J.T.; writing—review and editing, H.Z.; supervision, C.H.; funding acquisition, J.T. and H.Z. All authors have read and agreed to the published version of the manuscript.

**Funding:** This work was supported by the National Natural Science Foundation of China (61806088), by the Opening Project of Jiangsu Key Laboratory of Advanced Numerical Control Technology (SYKJ201804), by the Project funded by Jiangsu Province Postdoctoral Science Foundation (2019K041), and by Changzhou Sci&Tech Program (CE20195030).

**Acknowledgments:** We are grateful to our anonymous referees for their useful comments and suggestions. The authors also thank Honghui Fan, Yijun Liu, Yan Wang, Wei Gao and Jie Zhang for their useful advice during this work.

**Conflicts of Interest:** The authors declare no conflict of interest.
