Analysis of conditions that influence the properties of the constructed 3D-image features
N.G. Fedotov, A.A. Syemov, A.V. Moiseev

 

Penza State University, Penza, Russia,
LLC «KomHelf», Penza, Russia,
Penza State Technological University, Penza, Russia

Full text of article: Russian language.

 PDF

Abstract:
In this article, we discuss theoretical results obtained using a new geometric method for 3D image analysis and recognition (a hypertrace transform). A mathematical model of the proposed method is briefly described. The theory of 3D image hypertriplet features with analytical structure is further developed. The feature properties are studied while they are being formed using a newly developed mathematical tool – a hypertrace matrix. The feature properties depend on a specific formation process and processing results of the hypertrace matrix.

Keywords:
image, hypertrace transform, hypertrace matrix, hypertriplet feature, support grid on the sphere, features analytical structure.

Citation:
Fedotov NG, Syemov AA, Moiseev AV. Analysis of conditions that influence the properties of the constructed 3D-image features. Computer Optics 2016; 40(6): 887-894. DOI: 10.18287/2412-6179-2016-40-6-887-894.

References:

  1. Fedotov NG. The theory of pattern recognition features based on stochastic geometry and functional analysis [In Russian]. Moscow: “Fizmatlit” Publisher; 2010. ISBN: 978-5-9221-0996-3.
  2. Kiy KI. Segmentation and detection of contrast objects and their application in robot navigation. Pattern Recognition and Image Analysis 2015; 25(2): 338-346. DOI: 10.1134/S1054661815020145.
  3. Wang C, Huang K-Q. VFM: visual feedback model for robust object recognition. Journal of Computer Science and Technology 2015; 30(2): 325-339. DOI: 10.1007/s11390-015-1526-1.
  4. Zhang Y, Song S, Tan P, Xiao J. PanoContext: A whole-room 3D context model for panoramic scene understanding. ECCV 2014; VI(8694): 668-686. DOI: 10.1007/978-3-319-10599-4_43.
  5. Andreux M, Rodolà E, Aubry M, Cremers D. Anisotropic Laplace-Beltrami operator for shape analysis. ECCV 2014; VI(8928): 299-312. DOI: 10.1007/978-3-319-16220-1_21.
  6. Elhachloufi M, El Oirrak A, Aboutajdine D, Kaddioui MN. Affine invariant descriptors of 3D object using multiple regression model. International Journal of Computer Science & Information Technology 2011; 3(1): 1-10. DOI: 10.5121/ijcsit.2011.3101.
  7. Fedotov NG, Ryndina SV, Syemov АА. Trace transform of spatial images. 11th International conference on Pattern Recognition and Image Analysis: New Information technologies (PRIA-11-2013). Conference Proceedings. Samara, Russia: IPSI RAS; 2013; 1: 186-189.
  8. Fedotov NG, Ryndina SV, Syemov АА. Trace transform of three-dimensional objects: recognition, analysis and database search. Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications 2014; 24(4): 566-574. DOI: 10.1134/S105466181404004X.
  9. Semov AA. The basic methods of hypertrace-matrix formation [In Russian] // 21st century: Results of the Past and Problem of the Present plus. Scientific and methodical magazine. Series: Engineering science. Information technologies 2015; 03(25): 69-76.
  10. Fedotov NG. The Theory of Image-Recognition Features Based on Stochastic Geometry. Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications 1998; 8(2): 264-266.
  11. Fedotov NG, Semov AA, Moiseev AV. Feature space minimization of three-dimensional image recognition based on stochastic geometry and functional analysis [In Russian]. Machine Learning and Data Analysis 2015; 1(13): 1796-1814. DOI: 10.21469/22233792.1.13.03.
  12. Fedotov NG, Syemov AA, Moiseev AV. Intelligent capabilities hypertrace transform: Constructing features with predetermined properties [In Russian]. Machine Learning and Data Analysis 2014; 1(9): 1200-1214.
  13. Fedotov NG, Syemov AA. Hypertrace-matrix as main tool for 3D objects analysis [In Russian]. 21st century: Results of the Past and Problem of the Present plus. Scientific and methodical magazine. Series: Engineering science. Information technologies 2015; 03(25): 63-69.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20