In order to realize the retrieval efficiency and detection precision of digital library collection resources, a new clustering algorithm (Fast density peak clustering,FDPC) based on fast texture density peak is proposed. Firstly, a framework of document image retrieval based on content description is given, based on median filter and direct-square equalization strategy, denoising and background processing of input document image are introduced, then density peak clustering (DPC) is used to classify image, and the convergence performance of DPC algorithm is improved by using dynamic truncation distance mode. Finally, based on the library standard test library (Corel), the performance of the proposed algorithm is validated experimentally, and the experimental results show that the proposed method has higher retrieval efficiency and retrieval accuracy.