A video coloring method based on gabor feature space

Abstract

The invention discloses a video dyeing method based on a Gabor feature space. The video dyeing method based on the Gabor feature space comprises creating a rotation invariant Gabor filter and a Gabor feature space by using the texture feature of a video and generating Gabor current of the video and choosing keys. The keys are firstly to be dyed and then the color of the keys is spread between video frames according to a computed result of the Gabor current. Users can modify the color of a part where a high error of dyeing effect exists through an interactive operation. The video dyeing method based on the Gabor feature space is simple, easy to use, applicable to all kinds of video data with regional textures, capable of being completed on a graphics hardware graphics processing unit (GPU) platform, and fast in operation speed.

Description

technical field [0001] The invention belongs to the technical fields of computer algorithm, computer graphics technology, image processing technology and texture generation, and specifically relates to a video coloring method based on Gabor feature space, which can be used in application fields such as movie animation and multimedia editing. Background technique [0002] Image coloring is a processing technique that converts a monochrome grayscale image into a color image. Since the color information of the image is increased from one-dimensional grayscale information to three-dimensional RGB color information during the dyeing process, the reconstruction of this information usually requires the user's interpretation and assumptions about the grayscale image as constraints, and the color information is optimized through an optimized method. [A. Levin, D. Lischinski, and Y. Weiss. Colorization using optimization. ACM Trans. Graph., vol.23, no.3, pp.689-694, 2004.]. Some colo...

AI Technical Summary

Problems solved by technology

In this regard, the method of motion estimation is generally used, but the image feature operators usually used are difficult to ensure effective calculation

For example, SIFT (Scale-invariant feature transform), although it has the characteristics of robustness, does not conform to the characteristics of video coloring, and it is difficult to be used for color propagation and tracking

And for SIFT flow [C.Liu, J.Yuen, A.Torralba, J.Sivic, and W.Freeman, "SIFT flow: dense correspondence across different scenes," in Proc.ECCV2008, 2008, pp.28-42. ], its texture feature detection pays more attention to the comparison of feature points in the texture area. Therefore, when it is applied to video data with natural scenes, its texture feature detection is prone to errors, which affects the coloring effect of natural landscapes, because many natural scenes Textures in usually appear as some smooth transition visual and color effects

Images