Abstract
This chapter describes different segmentation algorithms, which is the process of dividing the image into homogeneous regions, where all the pixels that correspond to an object in the scene are grouped together. The grouping of pixels in regions is based on a homogeneity criterion that distinguishes them from one another. Segmentation algorithms based on criteria of similarity of pixel attributes (color, texture, etc.) or based on geometric criteria of spatial proximity of pixels (Euclidean distance, etc.) are reported. These criteria are not always valid, and in different applications it is necessary to integrate other information in relation to the a priori knowledge of the application context (application domain). In this last case, the grouping of the pixels is based on comparing the hypothesized regions with the a priori modeled regions. Many segmentation algorithms are available. Here, we present various segmentation strategies based on contour, threshold, region growing and merging, watershed transform, texture, mean-shift and using clustering-based algorithms (K-mean) to handle complex images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The word raster derives from television technology to indicate the horizontal scan of a monitor’s video signal. In computer graphics it is a term used to indicate the grid (matrix) of pixels constituting a raster image or bitmap image.
- 2.
This SSD of squared Euclidean distance coincides with the normal measure of match (similarity) formulated with the Sum of Squared Differences - SSD.
- 3.
See par. 1.9.4 Vol. III for a complete description of Parzen’s window based non-parametric classifier.
- 4.
Under the condition that \(\{\mathbf {x}_1,\ldots , \mathbf {x}_n\)} are independent and identically distributed random variables.
- 5.
Hence the name of kernel density estimation (KDE). Often these basic kernel functions (indicating a profile) are indicated by the lowercase letter \(k(\bullet )\).
- 6.
In our experiments \( c_d = 1 \).
- 7.
In this case \(g(x)=1\).
References
K. Karhunen, Uber lineare methoden in der wahrscheinlichkeitsrechnung. Ann. Acad. Sci. Fennicae. Ser. A. I. Math.-Phys. 37, 1–79 (1947)
M. Loève, Probability Theory I, vol. I, 4th edn. (Springer, Berlin, 1977)
D.E. Knuth, Art of Computer Programming, Volume 1: Fundamental Algorithms, 7th edn. (Addison-Wesley, Boston, 1997). ISBN 0201896834
M.S.H. Khayal, A. Khan, S. Bashir, F.H. Khan, S. Aslam, Modified new algorithm for seed filling. Theor. Appl. Inf. Technol. 26(1) (2011)
T. Pavlidis, Contour filling in raster graphics. ACM Comput. Graph. 15(3), 29–36 (1981)
A. Distante, N. Veneziani, A two-pass algorithm for raster graphics. Comput. Graph. Image Process. 20, 288–295 (1982)
J. Illingworth, J. Kittler, A survey of efficient hough transform methods. Comput. Vis., Graph., Image Process. 44(1), 87–116 (1988)
P.V.C. Hough, A method and means for recognising complex patterns. US Patent, p. US3069654 (1962)
R.O. Duda, P.E. Hart, Use of the hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11–15 (1972)
D.H. Ballard, Generalizing the hough transform to detect arbitrarys hapes. Pattern Recognit. (Elsevier) 13(2), 111–122 (1981)
L. Xu, E. Oja, P. Kultanena, A new curve detection method: randomized Hough transform (RHT). Pattern Recognit. Lett. 11, 331–338 (1990)
M.A. Fischler, R.C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
C. Lantuejoul, H. Digabel, Iterative algorithms, in In Actes du Second Symposium Europeen d’Analyse Quantitative des Microstructures en Sciences des Materiaux, Biologie et Medecine, pp. 85–99 (1978)
S. Beucher, C. Lantuej, Use of watersheds in contour detection, in Proceeding of Workshop on Image Processing, Real-time Edge and Motion Detection (1979)
S. Beucher, F. Meyer, The morphological approach to segmentation: the watershed transformation, in Mathematical Morphology in Image Processing, pp. 433–481 (1993)
J. Serra, Image Analysis and Mathematical Morphology (Academic Press, Cambridge, 1982)
L. Vincent, P. Soille, Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans. Pattern Anal. Mach. Intell. 13(6), 583–598 (1991)
R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, 2nd edn. (Wiley, Hoboken, 2001). ISBN 0471056693
D. Comaniciu, P. Meer, Mean-shift: a robust approach towards feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)
G.R. Bradski, Computer vision face tracking for use in a perceptual user interface. Intel Technol. J. (1998)
P. Meer, D. Comaniciu, V. Ramesh, Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–575 (2003)
J.G. Allen, R.Y.D. Xu, J.S. Jin, Object tracking using camshift algorithm and multiple quantized feature spaces, in Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing, pp. 3–7 (2004)
L. Tony, Scale-space theory: a basic tool for analysing structures at different scales. J. Appl. Stat. 21(2), 224–270 (1994)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Distante, A., Distante, C. (2020). Image Segmentation. In: Handbook of Image Processing and Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-42374-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-42374-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-42373-5
Online ISBN: 978-3-030-42374-2
eBook Packages: Computer ScienceComputer Science (R0)