Search

Cartoon-texture decomposition of images is a hot research topic in image processing, its main goal is to decompose a given image into cartoon and texture parts measured by different norms. In the existing partial decomposition model, the H−1 functional is often used to measure the oscillation function, which is obtained by the Hodge decomposition. Because a divergence-free vector function is neglected in the calculation of the Hodge decomposition, some directional information will be lost in the texture part, which will affect the decomposition results. In this paper, a new cartoon-texture decomposition model with divergence-free vector field constraint is established by analyzing the theory of the vector field. Mathematically, the new model makes the texture more accurate and complete. In order to solve this model, we transform the constrained optimization problem into an unconstrained problem by using the augmented Lagrange method, and then solve it with the alternating direction method. The proposed cartoon-texture decomposition model contains the divergence-free vector field information, so it improves the decomposition effect obviously, and the experimental results confirm the validity of the proposed model. [ABSTRACT FROM AUTHOR]

In most cases, the conventional pencil-drawing-synthesized methods were in terms of geometry and stroke, or only used classic edge detection method to extract image edge characters. In this paper, we propose a new method to produce pencil drawing from natural image. The synthesized result can not only generate pencil sketch drawing, but also can save the color tone of natural image and the drawing style is flexible. The sketch and style are learned from the edge of original natural image and one pencil image exemplar of artist’s work. They are accomplished through using the convolutional neural network feature maps of a natural image and an exemplar pencil drawing style image. Large-scale bound-constrained optimization (L-BFGS) is applied to synthesize the new pencil sketch whose style is similar to the exemplar pencil sketch. We evaluate the proposed method by applying it to different kinds of images and textures. Experimental results demonstrate that our method is better than conventional method in clarity and color tone. Besides, our method is also flexible in drawing style. [ABSTRACT FROM AUTHOR]