THE COMPONENT METHOD OF SCENE ANALYSIS AND OBJECT RECOGNITION

Authors

  • Aleksander Vechur
  • Aleksey Chayka
  • Yuriy Chemodakov

DOI:

https://doi.org/10.47839/ijc.2.2.204

Keywords:

Neural networks, Bayesian classifier, Pattern recognition, Grammar for syntax analysis

Abstract

The main aim of this work is to propose method that allows some machine to determine surrounding objects. It is important that algorithm must use small computer resources so that machine could work in real time. To improve segmentation on natural images, it is necessary to combine multiple features effectively. Our experimental results are consistent with the theoretical analysis.

References

S.Y. Kung. Digital Neural Networks. Engewood Cliffs. New Jersey: PTR Prentice Hall, 1994. p. 418.

Mona Sharma. Performance Evaluation of Image Segmentation and Texture Extraction Methods in Scene Analysis, to the University of Exeter as a thesis for the degree of Master of Philosophy in Computer Science, 2001.

C.T. Lin. Neural fuzzy systems: a neuro – fuzzy synergism to intelligent systems. C.S.G.Lee. Upper Saddle Rever, New Jersey: PTR Prentice Hall, 1997. p. 786.

T. Kohonen. Self-organizing Maps. Berlin: Springer-Verlag, 1995. p. 363.

P. Rummel, W. Beutel. Workpiece Recognition and Inspection by a Model-based Scene Analysis System, Pattern Recognition, Vol. 17, No. 1 (1984). pp.141-148.

A. R. Hanson, E.M. Riseman. VISIONS: A computer system for interpreting scenes, Computer Visions Systems (1978). Academic Press, New York. pp. 303-333.

X. Song, J. Sill, Y. Abu-Mostafa, H. Kasdan. Image recognition in context: application to microscopic urinalysis, Advances in Neural Information Processing Systems 963-969 (2000). MIT press, Cambridge, MA.

A. Torralba, P. Sinha. Statistical context priming for object detection. IEEE. Proc. Of Int. Conf. in Comp. Vision, Vol. 1 (2001). pp. 763-770.

Downloads

Published

2014-08-01

How to Cite

Vechur, A., Chayka, A., & Chemodakov, Y. (2014). THE COMPONENT METHOD OF SCENE ANALYSIS AND OBJECT RECOGNITION. International Journal of Computing, 2(2), 47-51. https://doi.org/10.47839/ijc.2.2.204

Issue

2003, Volume 2, Issue 2

Section

Articles

License

International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:
•    Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
•    Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
•    Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.