Fabric image recolorization is widely used in assisting designers to generate new color design proposals for fabric. In this paper, a new image recolorization method is proposed. Different from classical image recolorization methods, which need some complicated interactive operations from users, our proposed method can achieve automatic recolorization of images. The proposed method contains three sequential phases: a phase of extracting representative colors from fabric images; an image segmentation phase; and an image reconstruction phase by using given color themes. Integrated with intrinsic image decomposition, a new image segmentation model is designed in a variational framework, and an algorithm is given to solve the model. Our image recolorization results are images that are reconstructed by the composition of the image segmentation results and the given color themes. Numerical results demonstrate that our newly proposed intrinsic image decomposition-based image recolorization method can generate better results than the classical cartoon-and-texture decomposition-based method.

Saliency detection is an important but challenging task in the study of computer vision. In this article, we develop a new unsupervised learning approach for the saliency detection by an intrinsic regularization model, in which the Schatten-2/3 norm is integrated with the nonconvex sparse ${l_{2/3}}$ norm. The ${l_{2/3}}$ -norm is shown to be capable of detecting consistent values among sparse foreground by using image geometrical structure and feature similarity, while the Schatten-2/3 norm can capture the lower rank of background by matrix factorization. To improve effective performance of separation for Schatten-2/3-norm and ${l_{2/3}}$ -norm, a Laplacian regularization is adopted to the foreground for the smoothness. The proposed model essentially converts the required nonconvex optimization problem into the convex one, conducted by splitting the objective function based on singular value decomposition on one much smaller factor matrix and then optimized by using the alternating direction method of the multiplier. The convergence of the proposed algorithm is discussed in detail. Extensive experiments on three benchmark datasets demonstrate that our unsupervised learning approach is very competitive and appears to be more consistent across various salient objects than the current existing approaches.