好图像代码处理个人网站

这个页面编辑的有些惨烈，看这里吧： http://www.cs.cityu.edu.hk/~xbresson/ucla/code.html

This page provides Matlab codes. An Algorithm for Nonlocal TV Minimization, Matlab/C Code, June 25, 2009 A Fast Global Minimization Algorithm for Active Contour Models based on the Split-Bregman Method, Matlab/C Code, April 10, 2009 Active Contour with Shape Prior, Sept. 10, 2008 Fast Color Image Processing (Color Denoising and Color Deblurring), Aug. 5, 2007 A Global Minimization Algorithm of the Active Contour Model based on Chambolle's Projection Algorithm, Matlab Code, Aug. 1, 2007 Last update:June 25, 2009

An Algorithm for Nonlocal TV Minimization, Matlab/C Code, June 25, 2009

	PDFs:1. X. Bresson, "A Short Note for Nonlocal TV Minimization", Junel 2009 2.X. Zhang, M. Burger, X. Bresson and S. Osher, "Bregmanized Nonlocal Regularization for Deconvolution and Sparse Reconstruction", CAM Report 09-03, 2009
	Description:This is a short note to explain how to efficiently minimize the nonlocal Total Variation (NLTV) energy. The method is based on the Split-Bregman (SB), introduced by Goldstein-Osher, and extended to a nonlocal/graph version by Zhang-Burger-Bresson-Osher. For the 256x256 Barbara picture, the computation of weights takes around 1 second for a patch size 5x5 and a search window 11x11 and the NLTV minimization takes less 2 seconds. So, the total time for an image 256x256 for the NLTV minimization is less than 3 seconds. We also compare the SB version of NLTV with the dual version of NLTV, the NLH1, and the NL-Means. Experiments show that the SB-NLTV provides the best denoising result.
	Keywords:image denoising, Nonlocal Total Variation (NLTV), Split-Bregman method, Comparisons with nonlocal H1 and nonlocal Means
	Matlab/C Code

 

 

             

A Fast Global Minimization Algorithm for Active Contour Models based on the Split-Bregman Method, Matlab/C Code, April 10, 2009

	PDFs:1. X. Bresson, "A Short Guide on a Fast Global Minimization Algorithm for Active Contour Models", April 2009 2.T. Goldstein, X. Bresson and S. Osher, "Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction", CAM Report 09-06, 2009
	Description:A fast global minimization algorithm is developed to minimize a large class of segmentation models called active contours. We believe that the proposed theory and algorithm produce so far one of the most efficient minimization methods for the active contour segmentation problem. For example, the well-know cameraman picture, which size is 256x256, is segmented in less than 0.1 seconds. Besides, our algorithm, while being easier to code, produces results slightly faster than the popular and fast graph-cuts technique. Our algorithm is also more accurate than graph-cuts because it uses isotropic schemes to regularize the contour and is sub-pixel accurate. Besides, the memory requirement is low. Finally, the reader can make fast its own active contour model. We emphasized in the code the parts where the reader can add his/her own model.
	Keywords:segmentation, active contour, snake, global minimization, independence of initial position, ROF/TV model, Mumford-Shah energy, Chan-Vese model, fast minimization, Split-Bregman method, Comparison with Graph-Cuts

Matlab/C Code

	Fig. Segmentation of Smooth/Non-Texture Images.

	Fig. Segmentation of Texture Images.

Active Contour with Shape Prior, Sept. 10, 2008

	Implementation of the active contour with shape prior algorithmintroduced in X. Bresson, P. Vandergheynst and J. Thiran, "A Variational Model for Object Segmentation Using Boundary Information and Shape Prior Driven by the Mumford-Shah Functional",International Journal of Computer Vision (IJCV), Vol. 28, No 2, pp. 145 - 162, 2006
	Keywords:segmentation, active contour, shape prior, principal component analysis/pca, level set method, Mumford-Shah model
	Matlab/C Code

	Fig. Active Contour (dark) with shape prior (red). Case of missing information.

	Fig. Active Contour (dark) with shape prior (red). Case of occlusion and irregular boundary.

Fast Color Image Processing, (Color Denoising and Color Deblurring)  Aug. 5, 2007

	Implementation of the color image denoising algorithmintroduced in X. Bresson and T.F. Chan, "Fast Minimization of the Vectorial Total Variation Norm and Applications to Color Image Processing", CAM Report 07-25
	Keywords:color image denoising model, dual vectorial total variation (TV) norm, ROF model, deblurring, deconvolution

	Matlab Code for ColorDenoising

Fig 2a. Original Image

Fig 2b. Noisy Image

Fig 2c. Denoised Image

Fig. Denoising of a color picture with the vectorial ROF model. The denoising process takes a few seconds depending on your computer.

Matlab Code for ColorDeblurring

Fig 3a. Original Image

Fig 3b. Blurred and Noisy Image

Fig 3c. Deblurred Image

Fig. Deblurring of a color picture with the vectorial ROF model. The deblurring process takes a few seconds depending on your computer.

AGlobal Minimization of the Active Contour Model based on Chambolle's Projection Algorithm, Matlab Code, Aug. 1, 2007

	Implementation of the active contour model introduced in X. Bresson, S. Esedoglu, P. Vandergheynst, J. Thiran and S. Osher, "Fast Global Minimization of the Active Contour/Snake Model",Journal of Mathematical Imaging and Vision, 2007
	Keywords:active contour, snake, fast global minimization, independence of initial position, ROF model, Mumford-Shah energy
	Matlab Code

	Fig a. Original Image		Fig b. Segmentation Result		Fig c. Original Image		Fig d. Segmentation Result

Fig. Segmentation using the global active contour model. The segmentation process takes a few seconds depending on your computer.

来源：http://www.cs.cityu.edu.hk/~xbresson/ucla/code.html