Abstract
Image inpainting technique recovers the missing regions of an image using information from known regions and it has shown success in various application fields. As a popular kind of methods, Markov Random Field (MRF)-based methods are able to produce better results than earlier diffusion-based and sparse-based methods on inpainting images with big holes. However, for images with complex structures, the results are still not quite pleasant and some inpainting trails exist. The direction feature is an important factor for image understanding and human eye visual requirements, and exploiting multi-direction features is of great potential to further improve inpainting performance. Following the idea, this paper proposes a Structure Offsets Statistics based image inpainting algorithm by exploiting multiple direction features under the framework of MRF-based methods. Specifically, when selecting proper labels, multi-direction features are extracted and applied to construct a structure image and a non-structure image, and the candidate labels are chosen from the offsets of structure and non-structure images. Meanwhile, the multi-direction features are applied to construct a new smooth term for the energy equation which is then solved by graph-cut optimization technology. Experimental results show that on inpainting tasks with various complexities, the proposed method is superior to several state-of-the-art approaches in terms of the abilities of maintaining structure coherence and neighborhood consistence and the computational efficiency.
Highlights
Image inpainting, known as image completion, image restoration and image disocclusion, aims to recover the missing or degraded regions of an image in a visually plausibly way by using the known pixels of the image [1]
The methods can be grouped into two categories, i.e., greedy-based and Markov Random Field (MRF)-based methods
With the purposes of better maintaining structure coherence and neighborhood consistence for completing degraded images with large missing regions, this paper proposes a Structure Offsets Statistics based inpainting algorithm (Abbreviated as SOS) via in-depthly exploiting image direction features to guide inpainting process under the framework of MRF-based methods
Summary
Known as image completion, image restoration and image disocclusion, aims to recover the missing or degraded regions of an image in a visually plausibly way by using the known pixels of the image [1]. With the purposes of better maintaining structure coherence and neighborhood consistence for completing degraded images with large missing regions, this paper proposes a Structure Offsets Statistics based inpainting algorithm (Abbreviated as SOS) via in-depthly exploiting image direction features to guide inpainting process under the framework of MRF-based methods. (2) To better maintain neighborhood consistence, instead of only using color information, multi-direction features based on Curvelet transform are exploited to construct energy equation. In MRF-based methods, the known pixels/patches and the missing pixels/patches are regarded as labels and nodes, and how to assign labels or offsets is implemented by minimizing the energy equation. THE PROPOSED ALGORITHM To better maintain structure coherence and neighborhood consistence of the inpainted results, this paper proposes a structure offsets statistics based image inpainting algorithm using multi-direction features. The two main procedures as well as an analysis of the method are detailed
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have