Alexey Andriyashin

University of Joensuu, Joensuu, Province of Eastern Finland, Finland

Are you Alexey Andriyashin?

Claim your profile

Publications (4)0 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: In the research and investigation on the historical materials and cultural properties, not only conventional RGB digital images but also spectral reflectance images serve valuable information. However, some suitable techniques to extract effective information corresponding to the purpose of the use of the spectral reflectance images are desired because the spectral reflectance images have so huge of information. In this article, a method for investigating the historical materials and cultural properties will be described. This method can extract useful features relating to color compositions in the cultural properties. In this method, the measured spectral reflectance images of the icons, which are examples of the cultural properties, are clustered and the principal component analysis is applied in each cluster. The first principal component in each cluster is used for approximating the original spectral reflectance. The color difference caused of this approximation is calculated and used to control features to be extracted from the icons. Based on this number of clusters, results of the clustering are compared and possibilities of this method for further investigation are discussed.
    Journal of The Society of Photographic Science and Technology of Japan. 01/2011; 72(2):120-128.
  • Source
    A. Andriyashin, J. Parkkinen, T. Jaaskelainen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this study principal component analysis (PCA), non-negative matrix factorization (NMF) and non-negative tensor factorization (NTF) are applied as dimension reduction methods in color spectrum domain. The effect of light sources to the quality of the reconstructed spectrum is investigated. Due to the orthogonality, the corresponding bases vectors from PCA usually contain negative coefficients and are difficult to implement optically. NTF and NMF find non-negative basis for color spectrum space and are more suitable for optical implementation. Also the energy of NMF and NTF bases is more concentrated than PCA one. They should be more suitable for peaky light sources (i.e. Poly lux or LED) Five reflectance spectra sets from the different sources were used in tests. Four light source spectrums with the various shapes were applied for light source simulation. We evaluate reconstruction spectrum by quality and error measures including AE, GFC and PSNR.
    Pattern Recognition, 2008. ICPR 2008. 19th International Conference on; 01/2009
  • Source
    A. Kaarna, A. Andriyashin
    [Show abstract] [Hide abstract]
    ABSTRACT: Computation of the non-negative tensor factorization of a spectral image is very time-consuming. The computational complexity depends on the number of bases, i.e. the rank of the factorization, and on the dimensions of the spectral image. In this study we propose sampling methods for the preprocessing phase which enables a faster way to compute the non-negative tensor factorization (NTF). In the preprocessing both sampling and interpolation are applied to the original data. Three approaches are compared: direct sub-sampling, integer wavelet transform, and spectral smoothing. The experiments indicate that the preprocessing can remarkable reduce the time needed for NTF. From the approaches, the integer wavelet transform shows the best performance in computational and quality senses. The computational load from the direct subsampling is the lowest for one iteration, the spectral smoothing is computationally heaviest.
    Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International; 08/2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: The computation of non-negative tensor factorization may become very time-consuming when large datasets are used. This study shows how to accelerate NTF using multiresolution approach. The large dataset is preprocessed with an integer wavelet transform and NTF results from the low resolution dataset are utilized in the higher resolution dataset. The experiments show that the multiresolution based speed-up for NTF computation varies in general from 2 to 10 depending on the dataset size and on the number of required basis functions.
    Image Analysis, 15th Scandinavian Conference, SCIA 2007, Aalborg, Denmark, June 10-14, 2007, Proceedings; 01/2007