To inpaint the image with large damaged region and complex structure texture, a new method based on neighborhood reference priority which can not only maintain image character but also improve inpainting speed was proposed, by which the problem of image inpainting was translated into the best sample searching process. Firstly,the structure information of target image was extracted, and the sample region was divided into several sub-regions to reduce the sample size and the search scope. Secondly, in order to solve the problem that Sum of Squares of Deviations (SSD) method ignores the matching of structure information, structure symmetry matching constraint was introduced into matching method, which effectively avoided wrong matches and improves sample matching precision and searching efficiency. Then, priority formulas which highlights the effect of structure was obtained by introducing structure weight and confidence and combining the traditional priority calculation. Finally,the priority of four-neighborhood was got by computing overlapping information between target block and neighborhood blocks patches, according to the reliable reference information provided by four-neighborhood and the improved block matching method, the samples were pruned and the optimal sample was retrieved. The inpainting was completed until all the the optimal samples for all the target blocks were retrieved. The experimental results demonstrate that the proposed method can overcome the problems like texture blurring and structure dislocations and so on, the Peak Signal-to-Noise Ratio (PSNR) of the improved algorithm is increased by 0.5 dB to 1 dB compared with the contrast methods with speeding up inpainting process, the recovered image is much continuous for human vision. Meanwhile, it can effectively recover common damaged images and is more pervasive.

When inpainting the image of large damaged region with complex geometric structure and rich texture, the PatchMatch-based image inpainting algorithm has disadvantages like texture extension and some incorrect sample patches being selected as candidate patches. To solve these problems, a new image inpainting algorithm was proposed for improving accuracy and efficiency. In terms of exact matching of sample patches, an image was preprocessed to obtain priori information of the image, which was used to initialize the constraint of the offset map, while PathMatch algorithm used global random initialization. In the process of pixel patch matching, to improve the matching accuracy of the sample, mean method and angle method were introduced to compute the similarity of different categories of pixel patches. In terms of efficiency, according to the statistical characteristics of similar patches of an image, histogram statistical method was introduced to reduce the labels for inpainting. The proposed algorithm was verified by some instances. The simulation results show that compared with the original PatchMatch algorithm, the Peak Signal-to-Noise Ratio (PSNR) of the proposed algorithm was improved by 0.5dB to 1dB, and the running time was reduced by 5s to 10s, which indicates that the proposed algorithm can effectively improve the accuracy and efficiency of image inpainting.

The existing image completion methods have the problems of structural distortion on visual connectivity and easy to overfitting in the process of training. In order to solve the problems, a new image completion method of Generative Adversarial Network (GAN) based on two discrimination networks was proposed. One completion network, one global discrimination network and one local discrimination network were used in the completion model of the proposed method. The broken area of image to be completed was filled by a similar patch as input in the completion network, which greatly improved the speed and quality of the generation images. The global marginal structure information and feature information were used comprehensively in the global discrimination network to ensure that the completed image of completion network conformed visual connectivity. While discriminating the output image, the assisted feature patches found from multiple images were used to improve the generalization ability of discrimination in the local discrimination network, which solved the issue that the completion network was easily overfitting with too concentrated features or single feature. The experimental results show that, the proposed completion method has good completion effect on face images, and has good applicability in different kinds of images. The Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) of the proposed method are better than those of the state-of-the-art methods based on deep learning.

In order to solve the problem of inpainting missing information in the large damaged region with rich texture information and complex structure information, an image inpainting algorithm for partitioning feature subregions was proposed. Firstly, according to the different features contained in the image, the feature formula was used to extract the features, and the feature subregions were divided by the statistical eigenvalues to improve the speed of image inpainting. Secondly, on the basis of the original Criminisi algorithm, the calculation of priority was improved, and the structural fracture was avoided by increasing the influence of the structural term. Then, the optimal sample patch set was determined by using the target patch and its optimal neighborhood similar patches to constrain the selection of sample patch. Finally, the optimal sample patch was synthesized by using weight assignment method. The experimental results show that, compared with the original Criminisi algorithm, the Peak Signal-to-Noise Ratio (PSNR) of the proposed algorithm is improved by 2-3 dB; compared with the patch priority weight computation algorithm based on sparse representation, the inpainting efficiency of the proposed algorithm is also obviously improved. Therefore, the proposed algorithm is not only suitable for the inpainting of small-scale damaged images, but also has better inpainting effect for large damaged images with rich texture information and complex structure information, and the restored images are more in line with people's visual connectivity.

To effectively improve the denoising effect of the original anisotropic diffusion model that used only the 4 neighborhood pixels information and ignored the diagonal neighborhood pixels information of the pixel to be repaired in the image denoising process, a image denoising algorithm using UK-flag shaped anisotropic diffusion model was proposed. This model not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also used another 4 diagonal neighborhood pixels information in the denoising process. Then the model using the 8 direction pixels information for image denoising was presented, and it was proved to be rational. The proposed algorithm, the original algorithm, and an improved similar algorithm were used to remove the noise from 4 images with noise. The experimental results show that the proposed algorithm has an average increase of 1.90dB and 1.43dB in Peak Signal-to-Noise Ratio (PSNR) value respectively, and an average increase of 0.175 and 0.1 in Mean Structure Similitary Index (MSSIM) value respectively, compared with the original algorithm and the improved similar algorithm, which concludes that the proposed algorithm is more suitable for image denoising. algorithm not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also another 4 diagonal neighborhood pixels information was used in the denoising process, and the algorithm was proved to be rationality. The experimental results showed that the proposed algorithm could increase the PSNR (peak signal-to-noise ratio) value 1.69db, and the MSSIM(mean structure similitary index) value 0.14, compared with the other similar algorithms in image denoising, which conclud that this proposed algorithm is more suitable for image denoising.

Currently, various image inpainting algorithms based on Curvature-Driven Diffusion (CDD) model only make use of the reference information of four neighborhood pixels. Therefore, they cannot keep shape edges and their inpainting precisions high enough. To conquer these difficulties, the image inpainting algorithm based on double-cross CDD was presented, in which the reference information for damaged pixel was extended from four into eight neighborhood pixels. Firstly, one inpainting value for damaged pixel could obtain from the reference information of four neighborhood pixels using the original CDD algorithm. Secondly, another new inpainting value was computed with the newly introduced four neighborhood pixels. Finally, the final inpainting value was a weighted mean of the above-mentioned two inpainting computational value. The proposed method, original CDD algorithm and its improved editions were implemented and compared in the experiments. The experimental results show that the proposed algorithm can effectively improve the inpainting precision and keep shape edges without increasing time complexity.

Currently, template size of texture-based image inpainting algorithm is fixed. Therefore, when the template size is small, the inpainting accuracy improves, but time complexity increases substantially; on the contrary, when the size is large, the time complexity declines, but inpainting error rate increases significantly. Adaptive template size algorithm proposed in this paper can enlarge template size according to the change of expect and variance of grayscale value between current template and its expanded one. Meanwhile, this approach can reduce template size according to the match degree between template and exemplar. After adaptively determining the template size, texture-based image inpainting algorithm was improved and used in experiments. The experimental results show this approach can highly improve the inpainting accuracy with high efficiency.