Image inpainting algorithm based on edge reconstruction

A novel image inpainting algorithm based on edge reconstruction using combined approach capable to restore both image texture and structure is proposed in this paper. For edge and boundary detection and recovery a multi-stage edge detection procedure based on cubic splines is used. The choice of the current pixel to be recovered is decided using the fast marching approach. The Telea method or the exemplar based method are used after this depending on the classification of the regions where to-be-restored pixel is located. The performance of the proposed approach is demonstrated via several examples, showing the effectiveness of the proposed algorithm in removal of small and large objects from the test images.