Recent publications of Sergey Kucheryavskiy
These publications have been fetched automatically from AAU scientific database. For complete publications list, please, see a personal CV
01.
Chemical imaging and multivariate image analysis
Kucheryavskiy, S. 30 maj 2011Publikation: Forskning › Konferenceabstrakt til konference
| Originalsprog | Engelsk |
|---|---|
| Udgivelsesdato | 30 maj 2011 |
| Antal sider | 1 |
| Status | Udgivet |
02.
Fast algorithm for exploring and compressing of large hyperspectral images
Kucheryavskiy, S. 6 jun 2011Publikation: Forskning - peer review › Paper uden forlag/tidsskrift
A new method for calculation of latent variable space for exploratory analysis and dimension reduction of large hyperspectral images is proposed. The method is based on significant downsampling of image pixels with preservation of pixels’ structure in feature (variable) space. To achieve this, information about pixels density in principal component space for the first two components is utilized. The method was tested on several hyperspectral images and showed significant improvement of performance while the orientation of the latent variables was not very different from the original one. The method can be used first of all for fast compression of large data arrays with principal component analysis or similar projection techniques.
| Originalsprog | Engelsk |
|---|---|
| Udgivelsesdato | 6 jun 2011 |
| Antal sider | 4 |
| DOI | |
| Status | Udgivet |
Workshop
| Workshop | WHISPERS 2011 |
|---|---|
| Land | Portugal |
| By | Lisbon |
| Periode | 06-06-11 → 09-06-11 |
03.
Extracting useful information from images
Kucheryavskiy, S. 15 aug 2011 I : Chemometrics and Intelligent Laboratory Systems. 108, 1, s. 2-12. 11 s.Publikation: Forskning - peer review › Tidsskriftartikel
The paper presents an overview of methods for extracting useful information from digital images. It covers various approaches that utilized different properties of images, like intensity distribution, spatial frequencies content and several others. A few case studies including isotropic and heterogeneous, congruent and non-congruent images are used to illustrate how the described methods work and to compare some of them
| Originalsprog | Engelsk |
|---|---|
| Tidsskrift | Chemometrics and Intelligent Laboratory Systems |
| Udgivelsesdato | 15 aug 2011 |
| Vol/bind | 108 |
| Tidsskriftsnummer | 1 |
| Sider | 2-12 |
| Antal sider | 11 |
| ISSN | 0169-7439 |
| DOI | |
| Status | Udgivet |
04.
Some developments in multivariate image analysis
Kucheryavskiy, S. 18 okt 2010Publikation: Forskning › Poster
Multivariate image analysis (MIA), one of the successful chemometric applications, now is used widely in different areas of science and industry. Introduced in late 80s it has became very popular with hyperspectral imaging, where MIA is one of the most efficient tools for exploratory analysis and classification. MIA considers all image pixels as objects and their color values (or spectrum in the case of hyperspectral images) as variables. So it gives data matrices with hundreds of thousands samples in the case of laboratory scale images and even more for aerial photos, where the number of pixels could be up to several million. The main MIA tool for exploratory analysis is score density plot – all pixels are projected into principal component space and on the corresponding scores plots are colorized according to their density (how many pixels are crowded in the unit area of the plot). Looking for and analyzing patterns on these plots and the original image allow to do interactive analysis, to get some hidden information, build a supervised classification model, and much more.
In the present work several alternative methods to original principal component analysis (PCA) for building the projection subspace have been considered in respect to MIA purposes. First of all, Robust PCA has been applied to several images with and without outliers. Being proposed as a method to deal with high-dimensional data, it suits the needs of MIA very well. Also several non-linear methods have been tried, including Principal Curves and Kernel PCA with different kernel functions. For some of the cases non-linear methods allowed to improve the results significantly giving scores plots where the pixels are organized more effectively according to the nature of the depicted areas and their properties. The detailed comparison of the methods using several examples will be shown.
In the present work several alternative methods to original principal component analysis (PCA) for building the projection subspace have been considered in respect to MIA purposes. First of all, Robust PCA has been applied to several images with and without outliers. Being proposed as a method to deal with high-dimensional data, it suits the needs of MIA very well. Also several non-linear methods have been tried, including Principal Curves and Kernel PCA with different kernel functions. For some of the cases non-linear methods allowed to improve the results significantly giving scores plots where the pixels are organized more effectively according to the nature of the depicted areas and their properties. The detailed comparison of the methods using several examples will be shown.
| Originalsprog | Engelsk |
|---|---|
| Udgivelsesdato | 18 okt 2010 |
| Status | Udgivet |
Konference
| Konference | International conference on Chemometrics in Analyticalal Chemistry |
|---|---|
| Land | Belgien |
| By | Antwerp |
| Periode | 18-10-10 → 21-10-10 |
05.
Monitoring of pellet coating process with image analysis—a feasibility study
Kucheryavskiy, S., Esbensen, K. & Bogomolov, A. 2010 I : Journal of Chemometrics. 24, 7-8, s. 472-480. 9 s.Publikation: Forskning - peer review › Tidsskriftartikel
Image analysis is an efficient technique used in many areas of science and industry. However, in process analytical applications it tends to be an ancillary tool, used mainly for visual monitoring or measuring some geometrical properties. At the same time, there are many other important aspects of the process samples appearance, besides measurable distances, that may be connected to the information of interest. In the present paper, the methods of image analysis were applied to at-line monitoring of fluid bed pellet coating process. The quantitative description of images of pellet samples, taken from different process stages, has been obtained using two different approaches: wavelet decomposition and angle measure technique (AMT). Both methods revealed a strong correlation between image features and process parameters. However, the AMT results turned out to be more accurate and stable. It has been shown that pellet images, taken with a conventional digital camera, can be used for at-line monitoring of the process course, specifically, the growth of pellets due to the coating. An algorithm for precise counting of pellets has been developed. Combined with the sample weighing, it enables an accurate determination of the mean added pellets’ weight. The method can be used for the determination of the mean layer thickness, either by itself for at-line analysis or as a reference technique, when modeling the process from in-line spectroscopy data.
| Originalsprog | Engelsk |
|---|---|
| Tidsskrift | Journal of Chemometrics |
| Udgivelsesdato | 2010 |
| Vol/bind | 24 |
| Tidsskriftsnummer | 7-8 |
| Sider | 472-480 |
| Antal sider | 9 |
| ISSN | 0886-9383 |
| DOI | |
| Status | Udgivet |
06.
Classification of crystal drops images
Kucheryavskiy, S. V., Belyaev, I. & Marquez, J. 2010Publikation: Forskning › Konferenceabstrakt til konference
| Originalsprog | Engelsk |
|---|---|
| Udgivelsesdato | 2010 |
| Antal sider | 2 |
| Status | Udgivet |
Konference
| Konference | Winter Symposium on Chemometrics |
|---|---|
| Nummer | 7 |
| Land | Rusland |
| By | Saint Petersburg |
| Periode | 15-02-10 → 19-02-10 |
