An Image Inpainting Method Based And Its Implementation On Image Retrieval

Image inpainting refers to the process of reconstructing the damaged image or removal of unwanted objects in the image. We need to take the most appropriate way of inpainting the image to its original state, while ensuring that the result achieves the best artistic effect. There are some methods commonly used, such as method based on the theory of PDE or based on texture synthesis. These methods performed well in detail reconstruction and regular texture synthesis cases respectively. But in cases that the damaged region is too large or a semantic fragment is completely missed, those old methods cannot do a good job. Rather than inpainting within the original image data, a way of inpainting using image content from other pictures will do help. As long as the improvement of research in image retrieval, we hope to take advantage of the good results by content-based image retrieval with particular criteria such as colors and semantics. With the image patches from the image retrieval results and appropriate image fusion technology (Graph Cuts and Poisson fusion in this article), we can do a better inpainting and achieve the result more in line with the visual effects. This dissertation elaborates the algorithm in detail and the improvement aim at the retrieval for image patches including the addition of relevance feedback, and finally shows an image retrieval platform we produced based on this algorithm which is designed easy to operate. A series of experiment results show the high efficiency and quality of the algorithm. And the unexpected result due to the random computation shows its creative accomplishment which makes this algorithm able to be applied to the image special effect processing.