350 rub
Journal Neurocomputers №10 for 2015 г.
Article in number:
Convolutional neural networks application for dust particles detection and recognition on microscopy images
Authors:
A.N. Kokoulin - Ph.D. (Eng.), Associate Professor, Perm National Research Polytechnic University. E-mail:liga_asu@mail.ru
Abstract:
This article define the design of the automated image analysis system of industrial dust particles for dust shape and component research using microscopic images of different scales. Industrial dusts are the air emulsions with hard particles of any sizes. The dust influence on population-s health is described as the superposition of particle sizes, their shape and chemical composition. The visual dust research is usually not automated. Due to this the probability of mistakes and misrecognitions is too high. And the automation of recognition process based on knowledge base of particle samples and wavelet analysis algorithms is expected to enhance the identification quality of large amounts of microscopic images. In this article we consider a novel approach based on wavelet transform for edge detection, simplified variant of active contour method for objects enumeration on image and convolutional neural networks for objects classification.
Pages: 10-15
References

 

  1. Jimoda L.A. Effects of Particulate Matter on Human Health, the Ecosystem, Climate and Materials: a Review // Facta Universitatis. Series: Working and living Environmental Protection. 2012. V. 9. № 1. R. 27-44.
  2. Cormier S., Lomnicki S., Backes W. Dellinger B. Origin and Health Impacts of Emissions of Toxic By-Products and Fine Particles from Combustion and Thermal Treatment of Hazardcomponentous Wastes and Materials // Environ Health Perspect. 2006. V. 114. № 6. R. 810-817.
  3. May I.V., Zagorodnov S.Yu., Maks A.A. Fractional and Component Composition of Dust in the Working Area of Machine Building Enterprise // Occupational Medicine and Industrial Ecology. 2012. V. 12. R. 12-16.
  4. Baswaraj D., Govardhan A., Premchand P. Active Contours and Image Segmentation: The Current State of Art Global journal of computer science and technology. 2012. V. 12.
  5. Chan T., Vese L. Active Contours Without Edges // IEEE Transactions on Image Processing. 2001. V. 10. R. 266-277.
  6. Lankton Sh., Tannenbaum A. Localizing Region-Based Active Contours // IEEE Trans Image Process. 2008. V. 17. № 11.  R. 2029-2039.
  7. Kass M., Witkin A., Terzopolous D. Snakes: Active Contour Models // International Journal of Computer Vision. 1988. V. 1. R. 321-331.
  8. Petrov V., Privalov O. The Modification of Active Contour Algorithm for the Interactive Segmentation of the Raster Images of Foundry Defects // Modern Problems of Science and Education. V. 6. R. 14-19.
  9. Yanowitz S., Bruckstein A. A New method for Image Segmentation // Computer Vision, Graphics and Image Processing. 1989. V. 46. R. 82-95.
  10. Hyung J.K. A Parallel Algorithm for the Biorthogonal Wavelet Transform Without Multiplication Parallel and Distributed Computing // Applications and Technologies Lecture Notes in Computer Science. 2007. V. 3320. R. 297-300.
  11. Simard P.Y., Steinkraus D., Platt J.C. Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis, Seventh International Conference on Document Analysis and Recognition (ICDAR) // IEEE Computer Society. Los Alamitos. 2003. R. 958-962.