Chemical Technology, Control and Management


The problem is formulated and methods for processing images, in particular pollen grains, based on the mechanisms for extracting statistical, dynamic, texture and specific characteristics, as well as geometric features of micro-objects, are developed. Methods are proposed for assessing the accuracy of processing information on the characteristics of points, point and non-linear verification of the contour of the input and reference images, highlighting, segmenting, contrasting, interpolating. The mechanisms of extracting frequency, cytoplasm, reticules, spores, textures, morphology, and geometric features of pollen grain images are studied. A set of programs for processing microobject images in C ++ language in the CUDA parallel computing environment has been implemented, including functional modules for reducing zero points of the contour, reducing raster dimensions, scaling, threshold and dynamic level control, adjusting color and brightness picture parameters, initial value, centroid, segment boundaries, orthogonal biquadratic identification polynomial.

First Page


Last Page





1. Alain Petrowski, Gerard Dreyfus, Claude Girault, “Performance Analysis of a Pipelined Backpropagation Parallel Algorithm”, IEEE Transactions on Neural Networks, vol. 4, no. 6, pp.970-981, 1993.

2. D.Banarse, I.France, A.W.G.Duller, Analysis of a self-organising image recognition neural network. L.: Advances in engineering software, 2000, 944 p.

3. A.Boucher, P.Hidalgo, M.Thonnat, J.Belmonte and C.Galán, “3-D pollen image recognition based on palynological knowledge, In 2nd European Symposium on Aerobiology, Vienna (Austria), 2000, pp. 3.

4. Artificial Neural Networks: Concepts and Theory, IEEE Computer Society Press, 1992, 132 p.

5. I.I.Jumanov, “Optimizasiya obrabotki izobrajeniy mikroobyektov na osnove rekurrentnogo obucheniya neyronnoy set ii implikativnogo otbora informativnix priznakov” [Optimization of image processing of microobjects based on recurrent neural network training and implicative selection of informative features], Problemi informatiki i energetiki, no. 4, pp.12, 2016.

6. Ulugbek Kh. Narzullayev, Olim I. Djumanov, Akmal R. Akhatov, “Information technologies for processing of microobjects images on the basis of neural networks with associative memory”, In proceedings of the 5th international conference on Asian Language Processing and Information Technology, 27-29 September, 2006, TUIT, Uzbekistan, Korea Information Processing Society, Korea, 2006, pp. 114-118.

Included in

Engineering Commons



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.