SaivDr Package

버전 4.2.2.2 (16.4 MB) 작성자: Shogo Muramatsu
System object definitions for sparsity-aware image and volumetric data restoration
다운로드 수: 1.8K
업데이트 날짜: 2023/4/30

SaivDr Package for MATLAB/Simulink View SaivDr Package on File Exchange

System object definitions for sparsity-aware image and volumetric data restoration

Summary

SaivDr is an abbreviation of Sparsity-Aware Image and Volumetric Data Restoration. This package is developed for

  • Experiments,
  • Development and
  • Implementation

of sparsity-aware image and volumetric data restoraition algorithms.

In particular, this package provides a rich set of classes related to non-separable oversampled lapped transform ( NSOLTs ) , which allows for convolutional layers with

  • Parseval tight (paraunitary),
  • Symmetric and
  • Multiresolution

properties. For some features, we have prepared custom layer classes with Deep Learning Toolbox. It is now easy to incorporate them into flexible configurations and parts of your network.

Information about SaivDr Package is given in Contents.m. The HELP command can be used to see the contents as follows:

   >> help SaivDr
    
   Sparsity-Aware Image and Volume Data Restoration Package
     
       Files
         mytest     - Script of unit testing for SaivDr Package
         quickstart - Quickstart of *SaivDr Package*
         setpath    - Path setup for *SaivDr Package*
      
       * Package structure
           
           + saivdr -+- testcase -+- dcnn
                     |            |
                     |            +- sparserep 
                     |            |                         
                     |            +- embedded                          
                     |            |
                     |            +- dictionary  -+- nsolt     -+- design
                     |            |               |
                     |            |               +- nsoltx    -+- design
                     |            |               |
                     |            |               +- nsgenlot  -+- design
                     |            |               |
                     |            |               +- nsgenlotx -+- design
                     |            |               |
                     |            |               +- olaols
                     |            |               |
                     |            |               +- olpprfb
                     |            |               |
                     |            |               +- udhaar 
                     |            |               |
                     |            |               +- generalfb
                     |            |               |
                     |            |               +- mixture
                     |            |               |
                     |            |               +- utility
                     |            |
                     |            +- restoration -+- ista
                     |            |               |
                     |            |               +- pds
                     |            |               |
                     |            |               +- metricproj
                     |            |               |
                     |            |               +- denoiser
                     |            |
                     |            +- degradation -+- linearprocess
                     |            |               |
                     |            |               +- noiseprocess
                     |            |
                     |            +- utility 
                     |
                     +- dcnn
                     |
                     +- sparserep
                     |                         
                     +- embedded
                     |
                     +- dictionary  -+- nsolt     -+- design
                     |               |             |
                     |               |             +- mexsrcs
                     |               |        
                     |               +- nsoltx    -+- design
                     |               |             |
                     |               |             +- mexsrcs
                     |               |
                     |               +- nsgenlot  -+- design
                     |               |         
                     |               +- nsgenlotx -+- design
                     |               |         
                     |               +- olaols
                     |               |         
                     |               +- olpprfb
                     |               |         
                     |               +- udhaar 
                     |               |
                     |               +- generalfb
                     |               |
                     |               +- mixture
                     |               |
                     |               +- utility
                     |
                     +- restoration -+- ista  
                     |               |
                     |               +- pds
                     |               |
                     |               +- metricproj
                     |               |
                     |               +- denoiser
                     |            
                     +- degradation -+- linearprocess
                     |               |
                     |               +- noiseprocess
                     |
                     +- utility

Requirements

  • MATLAB R2013b or later. R2021a is recommended.
  • Signal Processing Toolbox
  • Image Processing Toolbox
  • Optimization Toolbox

Recomendation

  • Deep Learning Toolbox
  • Global Optimization Toolbox
  • Parallel Computing Toolbox
  • MATLAB Coder
  • GPU Coder

Brief introduction

  1. Change current directory to where this file contains on MATLAB.

  2. Set the path by using the following command:

     >> setpath
    
  3. Build MEX codes if you have MATLAB Coder.

     >> mybuild
    
  4. Several example codes are found under the second layer directory 'examples' of this package. Change current directory to one under the second layer directiory 'examples' and execute an M-file of which name begins with 'main,' such as

     >> main_xxxx
    

    and then execute an M-file of which name begins with 'disp,' such as

     >> disp_xxxx
    

Contact address

 Shogo MURAMATSU,
 Faculty of Engineering, Niigata University,
 8050 2-no-cho Ikarashi, Nishi-ku,
 Niigata, 950-2181, JAPAN
 http://msiplab.eng.niigata-u.ac.jp/

References

  • Ruiki Kobayashi, Shogo Muramatsu, Shunsuke Ono, "Proximal Gradient-Based Loop Unrolling with Interscale Thresholding," Proc. Assoc. Annual Summit and Conf. (APSIPA ASC), Dec. 2021

  • Genki Fujii, Yuta Yoshida, Shogo Muramatsu, Shunsuke Ono, Samuel Choi, Takeru Ota, Fumiaki Nin, Hiroshi Hibino, "OCT Volumetric Data Restoration with Latent Distribution of Refractive Index," Proc. of 2019 IEEE International Conference on Image Processing (ICIP), pp.764-768, Sept. 2019

  • Yuhei Kaneko, Shogo Muramatsu, Hiroyasu Yasuda, Kiyoshi Hayasaka, Yu Otake, Shunsuke Ono, Masahiro Yukawa, "Convolutional-Sparse-Coded Dynamic Mode Decompsition and Its Application to River State Estimation," Proc. of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1872-1876, May 2019

  • Shogo Muramatsu, Samuel Choi, Shunske Ono, Takeru Ota, Fumiaki Nin, Hiroshi Hibino, "OCT Volumetric Data Restoration via Primal-Dual Plug-and-Play Method," Proc. of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.801-805, Apr. 2018

  • Shogo Muramatsu, Kosuke Furuya and Naotaka Yuki, "Multidimensional Nonseparable Oversampled Lapped Transforms: Theory and Design," IEEE Trans. on Signal Process., Vol.65, No.5, pp.1251-1264, DOI:10.1109/TSP.2016.2633240, March 2017

  • Kota Horiuchi and Shogo Muramatsu, "Fast convolution technique for Non-separable Oversampled Lapped Transforms," Proc. of Asia Pacific Signal and Information Proc. Assoc. Annual Summit and Conf. (APSIPA ASC), Dec. 2016

  • Shogo Muramatsu, Masaki Ishii and Zhiyu Chen, "Efficient Parameter Optimization for Example-Based Design of Non-separable Oversampled Lapped Transform," Proc. of 2016 IEEE Intl. Conf. on Image Process. (ICIP), pp.3618-3622, Sept. 2016

  • Shogo Muramatsu, "Structured Dictionary Learning with 2-D Non-separable Oversampled Lapped Transform," Proc. of 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2643-2647, May 2014

  • Kousuke Furuya, Shintaro Hara and Shogo Muramatsu, "Boundary Operation of 2-D non-separable Oversampled Lapped Transforms," Proc. of Asia Pacific Signal and Information Proc. Assoc. Annual Summit and Conf. (APSIPA ASC), Nov. 2013

  • Shogo Muramatsu and Natsuki Aizawa, "Image Restoration with 2-D Non-separable Oversampled Lapped Transforms," Proc. of 2013 IEEE International Conference on Image Process. (ICIP), pp.1051-1055, Sep. 2013

  • Shogo Muramatsu and Natsuki Aizawa, "Lattice Structures for 2-D Non-separable Oversampled Lapped Transforms," Proc. of 2013 IEEE International Conference on Acoustics, Speech and Signal Process. (ICASSP), pp.5632-5636, May 2013

Acknowledgement

This work was supported by JSPS KAKENHI Grant Numbers JP23560443, JP26420347 and JP19H04135.

Contributors

Developpers

  • Shintaro HARA, 2013-2014
  • Natsuki AIZAWA, 2013-2014
  • Kosuke FURUYA, 2013-2015
  • Naotaka YUKI, 2014-2015
  • Yuya KODAMA, 2020-
  • Yasas GODAGE, 2021-

Test contributers

  • Hidenori WATANABE, 2014-
  • Kota HORIUCHI, 2015-
  • Masaki ISHII, 2015-
  • Takumi KAWAMURA, 2015-
  • Kenta SEINO, 2015-
  • Satoshi NAGAYAMA, 2017-
  • Shota KAYAMORI, 2017-
  • Genki FUJII, 2017-
  • Naoki YAMAZAKI, 2017-
  • Yuhei KANEKO, 2017-
  • Nawapan LAOCHAROENSUK, 2019-
  • Yusuke ARAI, 2020-

인용 양식

Shogo Muramatsu (2024). SaivDr Package (https://github.com/msiplab/SaivDr/releases/tag/4.2.2.2), GitHub. 검색됨 .

MATLAB 릴리스 호환 정보
개발 환경: R2021a
R2015b 이상 릴리스와 호환
플랫폼 호환성
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

+saivdr/+dcnn

+saivdr/+dcnn/+mexsrcs

+saivdr/+degradation

+saivdr/+degradation/+linearprocess

+saivdr/+degradation/+noiseprocess

+saivdr/+dictionary

+saivdr/+dictionary/+generalfb

+saivdr/+dictionary/+mixture

+saivdr/+dictionary/+nsgenlot

+saivdr/+dictionary/+nsgenlot/+design

+saivdr/+dictionary/+nsgenlotx

+saivdr/+dictionary/+nsgenlotx/+design

+saivdr/+dictionary/+nsolt

+saivdr/+dictionary/+nsolt/+design

+saivdr/+dictionary/+nsolt/+mexsrcs

+saivdr/+dictionary/+nsoltx

+saivdr/+dictionary/+nsoltx/+design

+saivdr/+dictionary/+nsoltx/+mexsrcs

+saivdr/+dictionary/+olaols

+saivdr/+dictionary/+olpprfb

+saivdr/+dictionary/+olpprfb/+mexsrcs

+saivdr/+dictionary/+udhaar

+saivdr/+dictionary/+utility

+saivdr/+embedded

+saivdr/+restoration

+saivdr/+restoration/+denoiser

+saivdr/+restoration/+ista

+saivdr/+restoration/+metricproj

+saivdr/+restoration/+pds

+saivdr/+sparserep

+saivdr/+testcase/+dcnn

+saivdr/+testcase/+degradation

+saivdr/+testcase/+degradation/+linearprocess

+saivdr/+testcase/+degradation/+noiseprocess

+saivdr/+testcase/+dictionary/+generalfb

+saivdr/+testcase/+dictionary/+mixture

+saivdr/+testcase/+dictionary/+nsgenlot

+saivdr/+testcase/+dictionary/+nsgenlot/+design

+saivdr/+testcase/+dictionary/+nsgenlotx

+saivdr/+testcase/+dictionary/+nsgenlotx/+design

+saivdr/+testcase/+dictionary/+nsolt

+saivdr/+testcase/+dictionary/+nsolt/+design

+saivdr/+testcase/+dictionary/+nsoltx

+saivdr/+testcase/+dictionary/+nsoltx/+design

+saivdr/+testcase/+dictionary/+olaols

+saivdr/+testcase/+dictionary/+olpprfb

+saivdr/+testcase/+dictionary/+udhaar

+saivdr/+testcase/+dictionary/+utility

+saivdr/+testcase/+embedded

+saivdr/+testcase/+restoration

+saivdr/+testcase/+restoration/+denoiser

+saivdr/+testcase/+restoration/+ista

+saivdr/+testcase/+restoration/+metricproj

+saivdr/+testcase/+restoration/+pds

+saivdr/+testcase/+sparserep

+saivdr/+testcase/+utility

+saivdr/+utility

examples/dcnn

examples/dcnn/+support

examples/dirlot

examples/dirlot/+support

examples/icassp2013_rev

examples/icassp2013_rev/+support

examples/icassp2014

examples/icassp2014/+support

examples/icassp2014/ksvdsbox

examples/icassp2019

examples/icassp2019/+support

examples/icip2013_rev

examples/icip2013_rev/+support

examples/icip2016

examples/icip2016/+support

examples/icip2016/ksvdsbox

examples/icip2019

examples/icip2019/+testcases

examples/quickdesign

examples/rgbdemos

GitHub 디폴트 브랜치를 사용하는 버전은 다운로드할 수 없음

버전 게시됨 릴리스 정보
4.2.2.2

See release notes for this release on GitHub: https://github.com/msiplab/SaivDr/releases/tag/4.2.2.2

4.2.2.1

See release notes for this release on GitHub: https://github.com/msiplab/SaivDr/releases/tag/4.2.2.1

4.2.1.0

See release notes for this release on GitHub: https://github.com/msiplab/SaivDr/releases/tag/4.2.1.0

4.2.0.0

See release notes for this release on GitHub: https://github.com/msiplab/SaivDr/releases/tag/4.2.0.0

4.1.1.0

See release notes for this release on GitHub: https://github.com/msiplab/SaivDr/releases/tag/4.1.1.0

4.1.0.0

- SaivDr20200903
-- (Major) Created custom layer classes for Deep Learning Toolbox
--- saivdr.dcnn.*
--- examples/dcnn

4.0.0.0

- SaivDr20200229
-- (Major) Revised to use property 'NumberOfLevels' and deprecated to set nLevels argument for STEP methods
-- (Major) Start to support GPU Arrays
-- (Major) Enhanced volumetric data visualization
etc.

3.1.0.0

- SaivDr20180827
-- (Major) Added wrapper classes for parallel processing
--- saivdr.dictionary.olaols.*
--- saivdr.utility.OlsOlaProcess2d
--- saivdr.utility.OlsOlaProcess3d

3.0.0.0

- SaivDr20170504
-- (Major) Excluded the automatic MEX code generation functions
--- Prepared the code generation script MYBUILD instead
-- (Minor) Revised header comments of each file

2.2.0.0

- SaivDr20160610
-- (Minor) Removed the dependency on Global Optimization Toolbox when GA is not used
--- saivdr.dictionary.nsoltx.design.AbstNsoltDesignerGaFmin
-- (Minor) Added new sample codes
--- examples/icip2016

2.1.0.0

- SaivDr20160314
-- (Minor) Clarified the array dimension for code generation in R2016a
-- (Minor) Fixed test method calling

2.0.0.0

- SaivDr20151126
-- (Major) Migrated to GitHub
-- (Major) Option 'GradObj' became available for a single-level Type-I NSOLT
-- (Minor) Fixed a bug of frequency domain synthesis operations

1.14.0.0

- SaivDr20150902
-- (Minor) Fixed a bug and revised to support boundary operation of DecimationSystem and BlurSystem
-- (Minor) Added SURE-LET denoising scripts in examples/dirlot

1.13.0.0

- SaivDr20150610
-- (Major) Frequency domain analysis and synthesis operations became available
-- (Major) Different numbers settings became available for decimation factors

1.12.0.0

Added some empty folders which are used for storing some data but were unexpectedly removed from the package after uploading.

1.11.0.0

Added some empty folders which are used for storing some data but were unexpectedly removed from the package after uploading.

1.10.0.0

Required Products were revised.

1.9.0.0

- SaivDr20141206
-- (Major) Thoroughly revised NSOLT and NS-GenLOT codes for acceleration
-- (Major) 3-D Volume data processing became available
-- (Major) Type-II NSOLT with ps < pa became available

1.8.0.0

- SaivDr20140512
-- (Minor) Fixed a bug in a support function and updated data in examples/icassp2014

1.7.0.0

- SaivDr20140315
-- (Major) Added NS-GenLOT and DirLOT system classes
-- (Major) Introduced a new package for mixture of unitary transforms
-- (Minor) Added some sample codes in examples/icassp2014
-- etc.

1.6.0.0

- SaivDr20140202
-- (Minor) Fixed the name of the root folder.

1.5.0.0

- SaivDr20140202
-- (Major) Fixed some classes under saivdr.dictionary.nsolt.* to run without MATLAB Coder
-- (Minor) Fixed overwriting problem of files under examples
-- etc.

1.2.0.0

- SaivDr20140122
-- (Major) {GradientPursuit,IterativeHardThresholding}With{Nsolt,UdHaar} were removed and integrated into a new class {GradientPursuit,IterativeHardThresholding}.
-- (Minor) Bug in StepMonitoringSystem was fixed.
-- etc.

1.1.0.0

- SaivDr20140118
-- HTML document of Quickstart was revised.

1.0.0.0

이 GitHub 애드온의 문제를 보거나 보고하려면 GitHub 리포지토리로 가십시오.
이 GitHub 애드온의 문제를 보거나 보고하려면 GitHub 리포지토리로 가십시오.