Classification of Images Background Subtraction in Image Segmentation

Francesco Mola; Jaromír Antoch; Luca Frigau; Claudio Conversano

Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica (2016)

  • Volume: 55, Issue: 1, page 73-86
  • ISSN: 0231-9721

Abstract

top
Many image segmentation algorithms have been proposed to partition an image into foreground regions of interest and background regions to be ignored. These algorithms use pixel intensities to partition the image, so it should be good practice to choose an appropriate background color as different as possible from the foreground one. In the case of a unique digitizing operation the user can make the choice of background color by himself in order to obtain a good result in the segmentation process, but in the case of several digitizing operations it would be useful to automate the whole process by removing any decision of the user about the choice of background color. Furthermore modern instruments allow capturing images with a high resolution characterized by a huge number of pixels, and pose speed problems to the image segmentation algorithms based on an idea of local thresholding. In this work an approach that adapts a widely used method for detecting moving objects from a video, called background subtraction (foreground detection), to the image segmentation framework is introduced. This approach combines local and global thresholding techniques to take advantage of the computational efficiency of the former and the accuracy of the latter. It provides good results in segmentation, and allows automating the process when foreground color of images is not constant, as well as speeding it up significantly. An application to the real data concerning botanical seeds is presented in order to compare, from a statistical perspective, the results derived from the proposed approach with those provided by standard image segmentation methods.

How to cite

top

Mola, Francesco, et al. "Classification of Images Background Subtraction in Image Segmentation." Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica 55.1 (2016): 73-86. <http://eudml.org/doc/286716>.

@article{Mola2016,
abstract = {Many image segmentation algorithms have been proposed to partition an image into foreground regions of interest and background regions to be ignored. These algorithms use pixel intensities to partition the image, so it should be good practice to choose an appropriate background color as different as possible from the foreground one. In the case of a unique digitizing operation the user can make the choice of background color by himself in order to obtain a good result in the segmentation process, but in the case of several digitizing operations it would be useful to automate the whole process by removing any decision of the user about the choice of background color. Furthermore modern instruments allow capturing images with a high resolution characterized by a huge number of pixels, and pose speed problems to the image segmentation algorithms based on an idea of local thresholding. In this work an approach that adapts a widely used method for detecting moving objects from a video, called background subtraction (foreground detection), to the image segmentation framework is introduced. This approach combines local and global thresholding techniques to take advantage of the computational efficiency of the former and the accuracy of the latter. It provides good results in segmentation, and allows automating the process when foreground color of images is not constant, as well as speeding it up significantly. An application to the real data concerning botanical seeds is presented in order to compare, from a statistical perspective, the results derived from the proposed approach with those provided by standard image segmentation methods.},
author = {Mola, Francesco, Antoch, Jaromír, Frigau, Luca, Conversano, Claudio},
journal = {Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica},
keywords = {Image segmentation; background subtraction; foreground detection; thresholding; computational efficiency; classification trees; classification accuracy},
language = {eng},
number = {1},
pages = {73-86},
publisher = {Palacký University Olomouc},
title = {Classification of Images Background Subtraction in Image Segmentation},
url = {http://eudml.org/doc/286716},
volume = {55},
year = {2016},
}

TY - JOUR
AU - Mola, Francesco
AU - Antoch, Jaromír
AU - Frigau, Luca
AU - Conversano, Claudio
TI - Classification of Images Background Subtraction in Image Segmentation
JO - Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica
PY - 2016
PB - Palacký University Olomouc
VL - 55
IS - 1
SP - 73
EP - 86
AB - Many image segmentation algorithms have been proposed to partition an image into foreground regions of interest and background regions to be ignored. These algorithms use pixel intensities to partition the image, so it should be good practice to choose an appropriate background color as different as possible from the foreground one. In the case of a unique digitizing operation the user can make the choice of background color by himself in order to obtain a good result in the segmentation process, but in the case of several digitizing operations it would be useful to automate the whole process by removing any decision of the user about the choice of background color. Furthermore modern instruments allow capturing images with a high resolution characterized by a huge number of pixels, and pose speed problems to the image segmentation algorithms based on an idea of local thresholding. In this work an approach that adapts a widely used method for detecting moving objects from a video, called background subtraction (foreground detection), to the image segmentation framework is introduced. This approach combines local and global thresholding techniques to take advantage of the computational efficiency of the former and the accuracy of the latter. It provides good results in segmentation, and allows automating the process when foreground color of images is not constant, as well as speeding it up significantly. An application to the real data concerning botanical seeds is presented in order to compare, from a statistical perspective, the results derived from the proposed approach with those provided by standard image segmentation methods.
LA - eng
KW - Image segmentation; background subtraction; foreground detection; thresholding; computational efficiency; classification trees; classification accuracy
UR - http://eudml.org/doc/286716
ER -

References

top
  1. Badekas, E., Papamarkos, N., Automatic evaluation of document binarization results, . In: Progress in pattern recognition, image analysis and applications. Springer, Heidelberg, 2005. (2005) 
  2. Breiman, L., Friedman, J., Olshen, L., Stone, J., Classification and Regression Trees, . CRC Press, Boca Raton, FL, 1984. (1984) Zbl0541.62042
  3. Chan, T., Shen, J., Image Processing and Analysis. Stochastic Methods, . SIAM, Philadelphia, PA, 2005. (2005) MR2143289
  4. Crow, F., Summed-area tables for texture mapping, . In: SIGGRAPH ’84: Proceedings of the 11th annual conference on Computer graphics and interactive techniques, 1984, 207–212. (1984) 
  5. Hastie, T., Tibshirani, R., Friedman, J., The Elements of Statistical Learning: Data Mining, Inference, and Prediction, . 2nd ed., Springer, Heidelberg, 2009. (2009) Zbl1273.62005MR2722294
  6. Hunt, R. W. G., The Reproduction of Colour, . 6th ed., J. Wiley, Chichester, UK, 2004. (2004) 
  7. Mola, F., Siciliano, R., 10.1023/A:1018590219790, . Statistics and Computing 7 (1997), 209–216. (1997) DOI10.1023/A:1018590219790
  8. Munoz, X., Freixenet, J., Cufi, X., Mart, J., 10.1016/S0167-8655(02)00262-3, . Pattern Recognition Letters 24 (2003), 375–392. (2003) DOI10.1016/S0167-8655(02)00262-3
  9. Otsu, N., 10.1109/TSMC.1979.4310076, . IEEE Trans. on Systemn, Man and Cybernetics 9 (1979), 62–66. (1979) DOI10.1109/TSMC.1979.4310076
  10. Padmavathi, G., Subashini, P., Sumi, A., Empirical evaluation of suitable segmentation algorithms for IR images, . IJCSI Int. J. of Computer Science Issues 7 (2010), http://ijcsi.org/contents.php?volume=7&&issue=4. (2010) 
  11. Piccardi, M., Background subtraction techniques: a review, . IEEE Trans. on Systemn, Man and Cybernetics 4 (2004), 62–3104. (2004) 
  12. Sauvola, J., Pietikäinen, M., 10.1016/S0031-3203(99)00055-2, . Pattern Recognition 33 (2000), 225–236. (2000) DOI10.1016/S0031-3203(99)00055-2
  13. Shafait, F., Keysers, D., Breuel, T. M., Efficient implementation of local adaptive thresholding techniques using integral images, . In: Electronic Imaging 2008, International Society for Optics and Photonics, 2008. (2008) 
  14. Shapiro, L. G., Stockman, G. C., Computer Vision, . Prentice-Hall, New Jersey, 2001. (2001) 
  15. Šonka, M., Hlaváč, V., Boyle, R., Image Processing, Analysis, and Machine Vision, . 4th ed., Cengage Learning, UK, 2014. (2014) 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.