¹Beijing Key Laboratory of Information Services Engineering, Beijing Union University, Beijing 100101, China.
²College of Information Technology, Beijing Union University, Beijing 100101, China.

---

Abstract—This paper proposes an improved Criminisi image restoration algorithm that produces better repairs and reduces the computational time. First, we improved the priority calculation and included a step that transforms the original confidence term into an index to achieve a more precise repair. Second, in large damaged areas of an image, we use a local searching method to find the optimal matching block to speed up the repair process. Our experimental results show that the improved method significantly increased the speed of the method, effectively retained image structures, and produced better visual effects.

Index Terms—Texture synthesis, image restoration, priority, local matching.

[PDF]

Cite: Yue Chi, Ning He, Qi Zhang, "A Fast Image Restoration Method Based on an Improved Criminisi Algorithm," Journal of Computers vol. 12, no. 6, pp. 591-601, 2017.