PRINCIPAL GEODESIC ANALYSIS BOUNDARY DELINEATION WITH SUPERPIXEL-BASED CONSTRAINTS

Authors

  • Mateusz Baran Cracow University of Technology
  • Zbisław Tabor Cracow University of Technology

DOI:

https://doi.org/10.5566/ias.1712

Keywords:

constrained global optimization, pattern recognition, principal geodesic analysis, watershed segmentation

Abstract

In this paper an algorithm for accurate delineation of object boundaries is proposed. The method employs a superpixel algorithm to obtain an oversegmentation of the input image, used as a constraint in the task. A shape model is built by applying Principal Geodesic Analysis on angular representation of automatically placed uniformly distant landmark points. The shape model is used to detect the boundaries of an object on a given image by iterative elongation of a partial boundary along borders of superpixels. Contrary to many state-of-the-art methods, the proposed approach does not need an initial boundary. The algorithm was tested on two natural and two synthetic sets of images. Mean Dice coefficients between 0.91 and 0.97 were obtained. In almost all cases the object was found. In areas of relatively high gradient magnitude the borders are delineated very accurately, though further research is needed to improve the accuracy in areas of low gradient magnitude and automatically select the parameters of the proposed error function.

References

Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S,

SLIC Superpixels Compared to State-of-the-Art

Superpixel Methods. IEEE T Pattern Anal Mach Intell

:2274–82.

Ballard DH, 1981. Generalizing the Hough transform to

detect arbitrary shapes. Pattern Recogn 13, 111–22.

Beucher S, 1990. Segmentation d’Images et Morphologie

Mathematique, Ph.D. Thesis, E.N.S. des Mines de Paris.

Beucher S, Meyer F, 1993. The morphological approach

to segmentation: The watershed transformation. Math

Morphol Imag Proc 34:433–81.

Boykov Y, Veksler O, Zabih R, 2001. Fast approximate

energy minimization via graph cuts. IEEE T Pattern

Anal Mach Intell 23:1222–39.

Canny J, 1986. A Computational Approach to Edge

Detection. IEEE T Pattern Anal Mach Intell 8:679–98.

Cootes TF, Edwards GJ, Taylor CJ, 2001. Active

Appearance Models. IEEE T Pattern Anal Mach Intell

:681–5.

Cootes TF, Taylor CJ, Cooper DH, Graham J, 1995. Active

Shape Models-Their Training and Application. Comput

Vis Image Und 61:38–59.

Cristinacce D, Cootes T, 2008. Automatic feature

localisation with constrained local models. Pattern

Recogn 41:3054–67.

Dice LR, 1945. Measures of the Amount of Ecologic

Association Between Species. Ecology 26:297–302.

Felzenszwalb PF, Huttenlocher DP, 2005. Pictorial

Structures for Object Recognition. Int J Comput Vision

:55–79.

Fletcher P, Lu C, Pizer S, Joshi S, 2004. Principal geodesic

analysis for the study of nonlinear statistics of shape.

IEEE T Med Imaging 23:995–1005.

Kendall DG, 1984. Shape Manifolds, Procrustean Metrics,

and Complex Projective Spaces. B Lond Math Soc

:81–121.

Kendall DG, 1989. A Survey of the Statistical Theory of

Shape. Stat Sci 4:87–99.

King DE, 2009. Dlib-ml: A Machine Learning Toolkit. J

Mach Learn Res 10:1755–8.

Lai KW, Hum YC, Salim MIM, Ong SB, Utama NP,

Myint YM, Noor NM, Supriyanto E 2014. Review

on Segmentation of Computer-Aided Skeletal Maturity

Assessment. In: Advances in Medical Diagnostic

Technology, Lecture Notes in Bioengineering. Springer

Singapore, 1st ed., 23–51.

Lindner C, Bromiley PA, Ionita MC, Cootes TF, 2015.

Robust and Accurate Shape Model Matching Using

Random Forest Regression-Voting. IEEE T Pattern

Anal 37:1862–74.

Meyer F, 2001. An overview of morphological

segmentation. Int J Pattern Recogn Artif Intell 15:1089–

Meyer F, 2005. Morphological segmentation revisited. In:

Bilodeau M, Meyer F, Schmitt M, eds., Space, Structure

and Randomness, no. 183 in Lecture Notes in Statistics.

Springer New York, 315–47.

Meyer F, Beucher S, 1990. Morphological segmentation. J

Vis Commun Image R 1:21–46.

Neubert P, Protzel P, 2014. Compact Watershed

and Preemptive SLIC: On Improving Trade-offs

of Superpixel Segmentation Algorithms, in: 2014

nd International Conference on Pattern Recognition

(ICPR), 996–1001.

Sirovich L, Kirby M, 1987. Low-dimensional procedure for

the characterization of human faces. J Opt Soc Am A 4,

Sommer S, Tatu A, Chen C, Jurgensen DR, de Bruijne

M, Loog M, Nielsen M, Lauze F, 2009. Bicycle

chain shape models, in: 2009 IEEE Computer

Society Conference on Computer Vision and Pattern

Recognition Workshops, 157–63.

Sommer S, Lauze F, Hauberg S, Nielsen M, 2010. Manifold

Valued Statistics, Exact Principal Geodesic Analysis

and the Effect of Linear Approximations, in: Daniilidis

K, Maragos P, Paragios N (Eds.), Computer Vision –

ECCV 2010. Springer Berlin Heidelberg. number 6316

in Lecture Notes in Computer Science, 43–56.

Srivastava A, Turaga P, Kurtek S, 2012. On advances in

differential-geometric approaches for 2D and 3D shape

analyses and activity recognition. Image Vis Comput

:398–416

Tabor Z, 2010. Surrogate Data: A Novel Approach to Object

Detection. Int J Appl Math Comput Sci 20:545–53.

Veksler O, Boykov Y, Mehrani P, 2010. Superpixels and

Supervoxels in an Energy Optimization Framework.

In: Computer Vision ECCV 2010, Lecture Notes in

Computer Science. Springer, Berlin, Heidelberg.

Wojciechowski W, Molka A, Tabor Z, 2016. Automated

measurement of parameters related to the deformities

of lower limbs based on x-rays images. Comput Biol

Med 70:1–11.

Downloads

Published

2017-12-18

Issue

Section

Original Research Paper

How to Cite

Baran, M., & Tabor, Z. (2017). PRINCIPAL GEODESIC ANALYSIS BOUNDARY DELINEATION WITH SUPERPIXEL-BASED CONSTRAINTS. Image Analysis and Stereology, 36(3), 223-232. https://doi.org/10.5566/ias.1712