inpainting
所属分类:matlab编程
开发工具:matlab
文件大小:1728KB
下载次数:1249
上传日期:2007-07-21 10:05:18
上 传 者:
dormice1981
说明: object removal在图像处理中的意思是用户可以随意擦去图像中的一个物体,算法可以自动的用背景中的信息补去空洞,达到看不出来是处理过的效果,又叫inpainting,该程序由matlab写成,效果非常好,文档、演示、测试图像均齐全
(object removal in image processing means that users can remove images of an object, the algorithm can automatically use the background information to fill empty, reaching out is not to look over the effectiveness of treatment, also known as inpainting, the program by matlab languages, has very good results, documents, presentations, test images have complete)
文件列表:
inpainting (0, 2004-11-29)
inpainting\bestexemplarhelper.c (2177, 2004-11-29)
inpainting\bungee0.png (146083, 2004-11-28)
inpainting\bungee1.png (122960, 2004-11-29)
inpainting\bungeeA.png (111352, 2004-11-29)
inpainting\bungeeP2.png (33537, 2004-11-29)
inpainting\bungeeP5.png (233955, 2004-11-29)
inpainting\bw0.png (1327, 2004-11-29)
inpainting\bw1.png (1819, 2004-11-29)
inpainting\bw2.png (1609, 2004-11-29)
inpainting\bwA.png (1327, 2004-11-29)
inpainting\bwP2.png (11889, 2004-11-29)
inpainting\bwP5.png (14368, 2004-11-29)
inpainting\index.html (10667, 2004-11-29)
inpainting\inpaint.m (5936, 2006-11-16)
inpainting\isophote.png (34114, 2004-11-29)
inpainting\plotall.m (580, 2004-11-29)
inpainting\slide.html (592, 2004-11-29)
inpainting\slide.png (308239, 2004-11-29)
inpainting\slide.ppt (408064, 2004-11-29)
inpainting\slidesmall.png (394123, 2004-11-29)
CS7495 Final Project
Sooraj Bhat
Object Removal by Exemplar-based Inpainting
USING THE CODE
Everything was done in Matlab and MEX (i.e. a C function callable from
Matlab). First, the C code needs to be compiled. At the Matlab
prompt, type:
mex bestexemplarhelper.c
You should then be able to run the following (which takes ~2mins on my
2GHz Pentium 4 laptop with 256MB of RAM):
[i1,i2,i3,c,d,mov] = inpaint('bungee0.png','bungee1.png',[0 255 0]);
A smaller run (~25 seconds) would be:
[i1,i2,i3,c,d,mov] = inpaint('bw0.png','bw2.png',[0 255 0]);
To visualize:
plotall;
close; movie(mov);
SAMPLE IMAGES & RESULTS
*0.png The original images ('bw' and 'bungee')
*{1,2}.png The different fill region masks.
*P2.png Plots of confidence and data terms.
*P5.png Plots of original, fill region, inpainted images and
confidence and data terms.
Other images in the dir contain redundant information. I didn't
include the movies since they are big, but they are available on my
project page (AVI format).
近期下载者:
相关文件:
收藏者: