Документ взят из кэша поисковой машины. Адрес оригинального документа : http://imaging.cs.msu.su/en/research/image
Дата изменения: Sat Apr 9 23:50:42 2016
Дата индексирования: Sat Apr 9 23:50:42 2016
Кодировка: UTF-8
Image processing | Laboratory of Mathematical Methods of Image Processing

Image processing

Image resampling

Andrey Nasonov, Alexey Lukin, Andrey Krylov

Reconstruction of a high-resolution image from a low-resolution image is a common problem in image processing.

We perform research in two directions:

  • Reconstruction of a high-resolution image as a solution of ill-posed inverse problem to the reconstruction of a low-resolution image from high-resolution one. Regularization methods are used to solve this problem.
  • Low-complexity image interpolation algorithms for realtime video conversion. Fast edge-directional resizing algorithms image and video are developed.

 

Image and video superresolution

Andrey Nasonov, Andrey Krylov

Using several low-resolution images can provide better quality of a high-resolution image. The process of recontructing a single high-resolution images from several low-resolution observations is called as superresolution.

Three directions are studied in this project:

  • High-quality superresolution based on regularization methods.
  • Non-iterative superresolution. A method of weighted median averaging is used to combine pixel values of given low-resolution images.
  • Superresolution for video sequencies. Two images are used here for high-resolution frame construction: current low-resolution frame and previous high-resolution frame.

 

Image enhancement

Andrey Nasonov, Alexey Lukin, Andrey Krylov

Application of regularization methods for image enhancement:

  • deblurring
  • deringing
  • denoising

 

Rank image filtering

Maria Storozhilova, Dmitry Yurin

Based on multiscale histograms and using lazy histogram updating technique we developed fast calculation scheme for finding:

  • Arbitrary rank element by neighbourhood
  • Mean by epsilon-V neighbourhood
  • Mean by KNV neighbourhood
  • Sliding equalization

 

Image metrics

res_metrics.png

Andrey Nasonov, Andrey Krylov

Image metrics are used to objective compare two images.

We consider the problem of evaluation of image enhancement algorithms like resampling, deringing, deblurring. The main idea is to find the areas where typical artifacts of image enhancement algorithms usually appear: blur and ringing artifacts.

 

Keypoints and descriptors

Dmitry Sorokin, Andrey Krylov

Keypoints detection and local image descriptors construction is one of the basic problems in image analysis.

The keypoints detection and descriptors construction algorithms are based on Gauss-Laguerre circular harmonic functions (CHFs) image expansion. The interconnection between Gauss-Laguerre CHFs and 2D Hermite functions in conjunction with fast Hermite projection method is used to accelerate the computation.

The subjects of current research:

  • Improvement of stability of Gauss-Laguerre keypoints descriptors to a class of projective and photometric transformations
  • Extension of keypoints detection and descriptors construction to color images