The objective evaluation method of printing image quality has not achieved good agreement with the subjective evaluation, and the bottom layer of the human vision is ignored. The characteristic visual similarity algorithm FSIM, which could extract the low-level features of the human vision, was applied in objective evaluation of the quality of the printed image, and used to evaluate the overall quality of the printed image in combination with subjective experiments. The mass fraction of FSIM algorithm was in the range of 0.9~1, in the correlation analysis with subjective evaluation, the CC value was 0.9490, the SROCC value was 0.9940, and the MAE value was 0.0049. Compared to MSE, PSNR, SSIM and MS-SSIM algorithms, the performance of this algorithm was better in stability, monotonic function and consistency. Experimental results showed that FSIM algorithm had a better consistency with subjective quality evaluation of the human eye, which was closer to the human visual system, and could effectively evaluate the quality of the printed image.