A novel total variation model based on kernel functions and its application
This work addresses image processing challenges, particularly for color images, but appears incremental as it builds on existing TV models.
The authors tackled the problem of image processing by proposing a novel total variation model based on kernel functions, which extends the generalized TV model and fuses information from color channels, with experiments demonstrating its effectiveness on gray and color images.
The total variation (TV) model and its related variants have already been proposed for image processing in previous literature. In this paper a novel total variation model based on kernel functions is proposed. In this novel model, we first map each pixel value of an image into a Hilbert space by using a nonlinear map, and then define a coupled image of an original image in order to construct a kernel function. Finally, the proposed model is solved in a kernel function space instead of in the projecting space from a nonlinear map. For the proposed model, we theoretically show under what conditions the mapping image is in the space of bounded variation when the original image is in the space of bounded variation. It is also found that the proposed model further extends the generalized TV model and the information from three different channels of color images can be fused by adopting various kernel functions. A series of experiments on some gray and color images are carried out to demonstrate the effectiveness of the proposed model.