Abstract

In the existing exemplar based image inpainting algorithms, the most similar match patches are used to inpaint the destroyed region, and they are searched in the whole source region in a fixed size. However, sometimes it would decrease the connectivity of structure and clearness of texture while increases the time complexity of this algorithm. To solve these problems, firstly we proposed an adaptive sample algorithm based on patch sparsity, it calculates the patch sparsity which divided the patches’ location into three types (smooth type, transition type and edge type). Then the size of the sample patch can be adaptively changed according to the type. Secondly it proposed a candidate patch system to improve the patch matching rate. From the result, we can see that the proposed method can match more significant patches than the traditional method, and it can give a better texture inpainting effect, especially when processing the complex and regular textures in the image which has a large destroyed region.

Highlights

  • The concept of digital image inpainting is firstly mentioned by Bertalmio[1] in 2000, for many reasons, one image may be destroyed by human, nature and other factors, some regions in the image may lost its information

  • ( pmax − pmin ) + pmin w0 is the standard sample size, it depends on the image size and the destroyed region size, here we use the fortieth of the destroyed region as it. pmax and pmin are the maximum and minimum of all the patch sparsity. λ1 and λ2 threshold set by the experience, here we set λ1equals 0.55 and λ2 equals 0.15

  • Two improvements are proposed to improve the correct matching rate, it can overcome the disadvantage made by the traditional exemplar-based method

Read more

Summary

Introduction

The concept of digital image inpainting is firstly mentioned by Bertalmio[1] in 2000, for many reasons, one image may be destroyed by human, nature and other factors, some regions in the image may lost its information. In the improved method[10], the author changed the traditional direction index and gave a new direction selection method, it can select more significant pixels and enhance the edge effect The proposed[15] introduced three basic techniques: copy-and-paste texture synthesis, geometric partial differential equations (PDEs), and coherence among neighboring pixels It combined these three building blocks in a variational model and completed to approximate the minimum of the proposed energy functional.To improve the result in a more natural quality with high performance, Chung introduced the minimum error boundary of cut technique into the exemplar-based method[16].

Theory of the exemplar-based method
Computing patch priorities
Propagating the texture and structure
Update the confidence values
Adaptive sample size algorithm
Candidate patch system
Experiment and result
Conclusion and future work

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.