Improvement of grayscale images of the basis of singular decomposition characteristics
DOI:
https://doi.org/10.34185/1562-9945-5-136-2021-03Keywords:
напівтонові зображення, рентген, контраст, роздільна здатність, синтез характеристик, ортогональні перетворення, сингулярне розкладання, візуальний аналізAbstract
The informational capabilities of the method for processing grayscale images aimed at increasing the sensitivity and reliability of their visual analysis are presented. Insufficient image quality is due to both the physical characteristics of the equipment used (background heterogeneity, nonlinearity of transmission characteristics of gray levels, noises of various origins), and the process of their formation (anatomical features of the patient, dynamic distortions, etc.). Improving medical images is an important step in obtaining reliable diagnostics when analyzing both with the naked eye (by a doctor) and when using automatic systems. One of the ways to solve the problem of increasing the sensitivity and reliability of identifying diagnostic parameters is the formation of a new space of features that allow us to determine the internal structure of the observed process, in particular, on the basis of orthogonal transformation of the initial data. The nontriviality of this stage is due to both the specificity of various types of images and the variety of tasks to be solved. The proposed algorithm is based on the process of multi-stage processing, including the expansion of the space of input features - the formation of a multidimensional ensemble based on the initial data using a window transformation, singular value decomposition, synthesis and visualization of new informative features. It is shown that the use of window processing for grayscale images allows to go to a multidimensional space and apply multidimensional processing methods, namely, a singular transformation, on the basis of which it is possible to increase the contrast, sensitivity and resolution of visual analysis. The information capabilities of new information characteristics obtained on the basis of the method of singular automorphic mapping (MSAO), which provides the formation of a multidimensional ensemble of images based on the initial data, its analysis as a whole, and anisotropic filtering in the two-dimensional plane of spatial frequencies, are considered. Experimental results are presented using real medical images as an example.
References
An analysis of x-ray image enhancement methods for vertebral bone segmentation IEEE 10th International Colloquium on Signal Processing & its Applications (CSPA2014) (7 - 9 Mac. 2014, Kuala Lumpur, Malaysia). 2014.
Р. 208-211.
M. S. V Sokashe, “Computer assisted method for cervical vertebrae segmentation from x-ray images,” Int. J. Adv. Res. Comput. Commun. Eng., vol. 2, no. 11, 2013, pp. 4387–4389.
Pearson, K. On lines and planes of closest fit to systems of points in space / K. Pearson // The London, Edinburgh and Dublin Philosophical Magazine and Journal of Sciences. – 1901. – Vol. 6, Issue 2. – P. 559-572.
Elsner J.B. Singular Spectrum Analysis. A New Тool in Time Series Analysis / J.B. Elsner, A.A. Tsonis. – N.Y.: Plenum Press, 1996. – 164 P.
Hoteling, H. Analysis of complex variables into principal components / H. Hoteling // Journal of Educational Psy- chology. – 1933. – Vol. 24, Issue 6. – P. 417-441.
Turk. M. Eigenfaces for Face Detection/Recognition / M. Turk and A. Pentland// J. Cogn. Neurosci.– 1991. – Vol. 3, No. 1. – P. 71–86.
Yang, J. Two-dimensional PCA: A new approach to ap- pearance-based face representation and recognition / J. Yang, D. Zhang, A.F. Frangi, J.-Y. Yang // IEEE Trans- actions on Pattern Analysis and Machine Intelligence. – 2004. – Vol. 26, Issue 1. – P. 131-137.
Akhmetshina L.G. Povysheniye chuvstvitel'nosti analiza rentgenovskikh snimkov metodom avtomorfnogo otobrazheniya v bazise sobstvennykh izobrazheniy / Akh-metshin A.M., Akhmetshina L.G. // Klinicheskaya informatika i telemeditsina. - 2008. - T. 4, - № 5. - S. 30-36.
Akhmetshina L.G. Adaptivnaya fil'tratsiya shumov v signalakh i izobrazheniya: metod selektivnogo singulyarnogo razlozheniya avtomorfnogo otobrazheniya. «Is-kusstvennyy intellekt» ÍPSHO MON i NAN Ukraí̈ni «Nauka í osvíta. 2005. №3,
S. 328-325.
