Aiming at the problem of object structure discontinuity and incompleteness occurred in image completion, an image completion algorithm based on depth information was proposed. Firstly, the plane parameter Markov random field model was established to speculate depth information of the pixels in the image where the scene situate, then the coplanar region in the image determined, and the target matching blocks were located. Secondly, according to the principle of perspective projection, the transformation matrix was derived, which guided the geometric transformation of the matching blocks. Finally, the target cost function which includes the depth term was designed. Experimental results show the proposed algorithm has superiority in both subjective details and Peak Signal-to-Noise Ratio (PNSR) statistics.

The traditional patch-based image completion algorithms circularly search the most similar patches in the whole image, and are easily affected by confidence factor in the process of structure propagation. As a result, these algorithms have poor efficiency and need a lot of time for the big computation. To overcome these shortages, a fast image completion algorithm based on randomized correspondence was proposed. It adopted a randomized correspondence algorithm to search the sample regions, which have similar structure and texture with the target region, so as to reduce the search space. Meanwhile, the method of computing filling priorities based on confidence factor and edge information was optimized to enhance the correctness of structure propagation. In addition, the method of calculating the most similar patches was improved. The experimental results show that, compared with the traditional algorithms, the proposed approach can obtain 5-10 times speed-up in repair rate, and performs better in image completion.