Filling holes in an image is achieved in a manner similar to peeling the onion. The order of filling affects the image inpainting results, especially concerning the content of complex images. When highresolution images are used to extract edge information, they are susceptible to high-frequency information, such as complex textures and noise. Furthermore, edge information is extracted in different resolutions, while the main contour information of the image can be obtained more easily. In this paper, multi-resolution information is used to prioritize which target patches in an image to fill, which helps to elucidate the optimal sequence for image repair. Multi-resolution images provide more information than single-resolution images, and similar patches are computed on multi-resolution images to obtain multiple candidate patches. Similar patch calculations use a variety of information on colors, gradients, and boundaries to more accurately search for similar patches. We chose the most reasonable candidate patch by means of the structural similarity index measure (SSIM). When pasting the patch to fill the target region, we used graph cut technology to eliminate blockiness. Compared with the state-of-the-art repair algorithm, the experimental results prove that the proposed repair algorithm can repair the image very well.INDEX TERMS Exemplar-based inpainting technique, priority calculation, patch matching, graph cut, multi-resolution information.
The classification of Thangka headdress has a wide application in the semantic retrieval and semantic annotation of Thangka. The existing classification methods are facing difficulties of segmentation which affects the practical application. In order to improve classification efficiency, this paper proposes a new method using support vector machine (SVM) for the classification of Thangka headdress with combination of multi-features. The new classification adopts the following steps: firstly, segment the Thangka headdress using Kirsh segmentation method; secondly, extract the features of Hu moments, Fourier moments, and Zernike moments; thirdly, extract the color features, the total being 35 features; finally, verify the classification accuracy using SVM, BP neural network and the random forest respectively. The classification result shows that SVM classification can achieve the best accuracy and the requirements of practical application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.