Study of informative feature selection approaches for the texture image recognition problem using Laws’ masks
V.V. Kutikova, A.V. Gaidel

 

Samara State Aerospace University, Samara, Russia,
Image Processing Systems Institute, Russian Academy of Sciences, Samara, Russia

Full text of article: Russian language.

 PDF

Abstract:
In this paper we discuss an image preprocessing method for different shooting conditions. The method can be applied in machine vision systems using a correlation-extremal mapping method. An information-theoretic method for image preprocessing based on entropy analysis is offered. The investigation of the method has shown that, when preprocessed, same-scene images obtained under different conditions have a more stable correlation coefficient than the original images.

Keywords:
texture analysis, Laws’ masks, feature selection, criterion of discriminant analysis, t-statistic.

Citation:
Kutikova VV, Gaidel AV. Study of informative feature selection approaches for the texture image recognition problem using the Laws’ masks. Computer Optics 2015; 39(5): 744-50.– DOI: 10.18287/0134-2452-2015-39-5-744-750.

References:

  1. Shapiro LG, Stockman GC. Computer Vision. N.J.: Rrentice-Hall; 2001.
  2. Fralenko VP. Methods of image texture analysis, Earth remote sensing data processing [In Russian]. Program systems: theory and applications 2014; 22(4): 19-39.
  3. Mollazade K, Omid M, Tab FA, Kalaj YR, Mohtasebi SS, Zude M. Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging. Computers and Electronics in Agriculture 2013; 98: 34-45.
  4. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. // IEEE Transactions on Systems, Man, and Cybernetics 1973; 3(6): 610-21.
  5. Petrou M, Sevilla PG. Image Processing: Dealing with Texture. John Wiley & Sons Ltd; 2006.
  6. Pratt W. Digital image processing. John Wiley & Sons; 1978.
  7. Laws KI. Rapid Texture Identification. SPIE 1980; 238: 376-80.
  8. Lee DC, Schenk T. Image segmentation from texture measurement. XVIIth ISPRS Congress. Technical Commission III: Mathematical Analysis of Data. Washington 1992; 195-9.
  9. Kupriyanov AV. Texture image segmentation based on estimating the local statistical features. [In Russian]. Herald of the Samara State Aerospace University 2008; 2(15): 245-51.
  10. Gaidel AV, Pervushkin SS. Research of the textural features for the bony tissue diseases diagnostics using the roentgenograms [In Russian]. Computer Optics 2013; 37(1): 113-9.
  11. Gaidel AV, Zelter PM, Kapishnikov AV, Khramov AG. Computed tomography texture analysis capabilities in diagnosing a chronic obstructive pulmonary disease [In Russian]. Computer Optics 2014; 38(4): 843-50.
  12. Gaidel AV, Larionova SN, Khramov AG. Research of the textural feactures for the nephrological diseases diagnostics using the ultrasound images [In Russian]. Herald of the Samara State Aerospace University 2014; 1(43): 229-37.
  13. Chandra B, Gupta M. An efficient statistical feature selection approach for classification of gene expression data. Journal of Biomedical Informatics 2011; 44: 529-35.
  14. Ilyasova NYu, Kupriyanov AV, Paringer RA. Formation of features for improving the quality of medical diagnosis based on discriminant analysis methods [In Russian]. Computer Optics 2014; 38(4): 851-5.
  15. Tsai CF, Eberle W, Chu CY. Genetic algorithms in feature and instance selection. Knowledge-Based Systems 2013; 39: 240-7.
  16. Rami NK, Al-Ani A, Al-Jumaily A. Feature subset selection using differential evolution and a statistical repair mechanism. Expert Systems with Applications 2011; 38(9): 11515-26.
  17. Kylberg texture dataset. Source: áhttp://www.cb.uu.se/~gus­taf/texture/ñ.
  18. Fukunaga K. Introduction to statistical pattern recognition. San Diego: Academic Press; 1990.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20