Image Restoration Using Piecewise Iterative Curve Fitting and Texture Synthesis

  title={Image Restoration Using Piecewise Iterative Curve Fitting and Texture Synthesis},
  author={Ke Sun and Yingyun Yang and Long Ye and Qin Zhang},
In this paper, we present a novel scheme for parsing images into medium level vision representation: contour curve and region texture. This scheme is integrated with piecewise iterative curve fittingand texture synthesis, in which an original image is analyzed at the representation side so as to obtain contours and local texture exemplars. The contour of each region will be processed piecewise by iterative curve-fitting procedure. At the reconstruction side, transmitted coefficients denoted to… 
Multi-Regions Texture Substitution for Image and Video
A multi-regions texture substitution (MRTS) algorithm for images and videos which can achieve mediumlevel-visual texture substitution through selecting the smallest region texture sample and which also can get good video reconstruction quality.
Hybrid MPI-OpenMP Parallelization of Image Reconstruction
This paper implements image reconstruction with a hybrid message passing interface (MPI) and OpenMP approach on the basis of a standard MPI implementation and shows that this approach can significantly improve time performance of image reconstruction algorithm.
Parallel multi-regions image restoration system and its implementation
  • J. Wan, Long Ye, Qin Zhang
  • Computer Science
    2010 3rd International Conference on Computer Science and Information Technology
  • 2010
The parallel multi-regions image restoration system is proposed in order to ensure the real-time application and can improve the restoration efficiency significantly and achieve optimal restoration.
A parallel framework for texture substitution coding
A distributed parallel TSC framework based on MPI is proposed and experiments have demonstrated that this parallel framework can improve the TSC efficiency significantly and achieve optimal restoration.
Manifold Adaptive Kernel Local Fisher Discriminant Analysis for Face Recognition
To efficiently cope with the high dimensionalities and complex nonlinear variations of face images in face recognition task, a novel manifold adaptive kernel local Fisher discriminant analysis


On pixel-based texture synthesis by non-parametric sampling
Unsupervised Segmentation of Color-Texture Regions in Images and Video
The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed and applying the criterion to local windows in theclass-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions.
Real-time texture synthesis by patch-based sampling
An algorithm for synthesizing textures from an input sample by sampling patches according to a nonparametric estimation of the local conditional MRF density function, to avoid mismatching features across patch boundaries.
Image quilting for texture synthesis and transfer
This work uses quilting as a fast and very simple texture synthesis algorithm which produces surprisingly good results for a wide range of textures and extends the algorithm to perform texture transfer — rendering an object with a texture taken from a different object.
Image compression using texture modeling
A statistical view of the texture parametrization using balanced multiwavelets and a hybrid image compression scheme are presented that can be seamlessly integrated in any embedded image coder while requiring minimal header data and the proposed hybrid codec is computationally-efficient.
Color image segmentation
  • Yining Deng, B. S. Manjunath, H. Shin
  • Computer Science
    Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)
  • 1999
In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented, where colors in the image are quantized to several representing classes that can be used to differentiate regions in the photo, thus forming a class-map of the image.
Improved H.264/AVC coding using texture analysis and synthesis
We assume that the textures in a video scene is classified into two categories: textures with unimportant subjective details and the remainder. We utilize this assumption for improved video coding
Sparse Representation for Color Image Restoration
This work puts forward ways for handling nonhomogeneous noise and missing information, paving the way to state-of-the-art results in applications such as color image denoising, demosaicing, and inpainting, as demonstrated in this paper.
Efficient contour-based shape representation and matching
A fast sub-optimal method for solving the correspondence problem between contour points from two shapes and results indicate that the proposed dissimilarity measure is aligned with human intuition.
Learning high-order MRF priors of color images
This paper introduces simplifications to the original approach by Roth and Black which allow us to cope with the increased clique size of color images, and introduces improvements over state-of-the-art monochromatic image priors.