By improving the 2D Hilbert-Huang transform method, a feature extraction method based on 2D variational mode decomposition (VMD) and Hilbert transform is proposed in this paper. Firstly, the partial discharge (PD) grayscale images are formed by the measured PD samples. Secondly, the PD grayscale images are decomposed by 2D VMD algorithm to obtain the modes on different center frequencies. Then, quaternion Hilbert transform are used to obtain the corresponding characteristic graphs, and the corresponding eigenvector of each PD sample is come into possession by the texture features of these graphs. Finally, the extracted feature quantities are recognized by BP neural network. The experimental results show that compared with 2D Hilbert-Huang transformation and grayscale feature extraction method, the extraction method proposed in this paper has a high correct recognition rate, and it verifies the feasibility of the feature extraction method. In addition, the 2D VMD-Hilbert method also provides a new idea for the spectrum analysis on PD signals.