tvreg 패키지 이미지 denoising, deconvolution과 inpainting을 수행하기 위해 총 편차 (TV) regularization을 적용합니다. 세 가지 잡음 모델이 지원됩니다 : 가우스 (L2), 라플라스 (L1) 및 Poisson 있습니다. 구현은 일반적인 TV 복원 문제 / 분 TV를 해결 (U) + | 람다 F (K * U, F) DX, U / denoising deconvolution, 그리고 특별한 경우로 inpainting을 수행할 수 있습니다. 그것은 효율적으로 최근의 분할 Bregman 방법을 사용하여 해결됩니다. 또한(translate from):The tvreg package applies total variation (TV) regularization to perform image denoising, deconvolution, and inpainting. Three different noise models are supported: Gaussian (L2), Laplace (L1), and Poisson. The implementation solves the general TV restoration problem / Min TV(u) + | lambda F(K*u,f) dx, u / to perform denoising, deconvolution, and inpainting as special cases. It is efficiently solved using the recent split Bregman method. Also included is an efficient implementation of Chan-Vese two-phase segmentation. All functions support grayscale, color, and arbitrary multichannel images.




File list:
tvreg
....\blurry.bmp

....\chanvese.c
....\chanvese.h
....\chanvese.m
....\chanvesecli.c
....\chanvesesimpleplot.m
....\chanvese_demo.bat
....\chanvese_demo.m
....\chanvese_demo.sh
....\cliio.c
....\cliio.h
....\compareimages.m
....\compile_mex.m
....\conv2padded.m
....\einstein.png

....\imageio.c
....\imageio.h
....\license.txt
....\lighthouse.bmp

....\makefile.gcc
....\makefile.vc
....\num.h
....\readme.txt
....\signal-D.bmp

....\signal-f.bmp

....\tvdeconv.m
....\tvdeconv_demo.bat
....\tvdeconv_demo.m
....\tvdeconv_demo.sh
....\tvdenoise.m
....\tvdenoise_demo.bat
....\tvdenoise_demo.m
....\tvdenoise_demo.sh
....\tvinpaint.m
....\tvinpaint_demo.bat
....\tvinpaint_demo.m
....\tvinpaint_demo.sh
....\tvreg.c
....\tvreg.h
....\tvreg.m
....\tvreg.pdf
....\tvregsimpleplot.m
....\tvrestore.m
....\tvrestorecli.c
....\wrench.bmp