Computer Vision

Living Edition
| Editors: Katsushi Ikeuchi (Editor-in-Chief)

Gradient Vector Flow

Living reference work entry



Related Concepts


Gradient vector flow is the vector field that is produced by a process that smooths and diffuses an input vector field and is usually used to create a vector field that points to object edges from a distance.


Finding objects or homogeneous regions in images is a process known as image segmentation. In many applications, the locations of object edges can be estimated using local operators that yield a new image called an edge map. The edge map can then be used to guide a deformable model, sometimes called an active contour or a snake, so that it passes through the edge map in a smooth way, therefore defining the object itself.

A common way to encourage a deformable model to move toward the edge map is to take the spatial gradient of the edge map, yielding a vector field. Since the edge map has its...

This is a preview of subscription content, log in to check access.


  1. 1.
    Hassouna MS, Farag AY (2009) Variational curve skeletons using gradient vector flow. IEEE Trans Pattern Anal Mach Intell 31(12):2257–2274CrossRefGoogle Scholar
  2. 2.
    Yu H, Chua CS (2006) GVF-based anisotropic diffusion models. IEEE Trans Image Process 15(6): 1517–1524CrossRefGoogle Scholar
  3. 3.
    Han X, Pham DL, Tosun D, Rettmann ME, Xu C, Prince JL, et al. (2004) CRUISE: cortical reconstruction using implicit surface evolution. NeuroImage 23(3):997–1012CrossRefGoogle Scholar
  4. 4.
    Miri MS, Robles VA, Abràmoff MD, Kwon YH, Garvin MK (2017) Incorporation of gradient vector flow field in a multimodal graph-theoretic approach for segmenting the internal limiting membrane from glaucomatous optic nerve head-centered SD-OCT volumes. Comput Med Imaging Graph 55:87–94CrossRefGoogle Scholar
  5. 5.
    Bai J, Shah A, Wu X (2018) Optimal multi-object segmentation with novel gradient vector flow based shape priors. Comput Med Imaging Graph 69: 96–111CrossRefGoogle Scholar
  6. 6.
    Xu C, Prince JL (1998a) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359–369MathSciNetCrossRefGoogle Scholar
  7. 7.
    Esteban CH, Schmitt F (2004) Silhouette and stereo fusion for 3D object modeling. Comput Vis Image Underst 96(3):367–392CrossRefGoogle Scholar
  8. 8.
    Han X, Xu C, Prince JL (2007) Fast numerical scheme for gradient vector flow computation using a multigrid method. IET Image Process 1(1):48–55CrossRefGoogle Scholar
  9. 9.
    Ren D, Zuo W, Zhao X, Lin Z, Zhang D (2013) Fast gradient vector flow computation based on augmented Lagrangian method. Pattern Recogn Lett 34(2):219–225CrossRefGoogle Scholar
  10. 10.
    Smistad E, Elster AC, Lindseth F (2015) Real-time gradient vector flow on GPUs using OpenCL. J Real-Time Image Process 10(1):67–74CrossRefGoogle Scholar
  11. 11.
    Smistad E, Lindseth F (2016) Multigrid gradient vector flow computation on the GPU. J Real-Time Image Process 12(3):593–601CrossRefGoogle Scholar
  12. 12.
    Xu C, Han X, Prince JL (2008) Gradient vector flow deformable models. In: Bankman I (ed) Handbook of medical image processing and analysis, 2nd edn. Academic Press, Cambridge, pp 181–194Google Scholar
  13. 13.
    Xu C, Prince JL (1998b) Generalized gradient vector flow external forces for active contours. Signal Process 71(2):131–139CrossRefGoogle Scholar
  14. 14.
    Jaouen V, Gonzalez P, Stute S, Guilloteau D, Chalon S et al (2014) Variational segmentation of vector-valued images with gradient vector flow. IEEE Trans Image Process 23(11):4773–4785MathSciNetCrossRefGoogle Scholar
  15. 15.
    Hafiane A, Vieyres P, Delbos A (2014) Phase-based probabilistic active contour for nerve detection in ultrasound images for regional anesthesia. Comput Biol Med 52:88–95CrossRefGoogle Scholar
  16. 16.
    Ray N, Acton ST (2004) Motion gradient vector flow: an external force for tracking rolling leukocytes with shape and size constrained active contours. IEEE Trans Med Imaging 23(12):1466–1478CrossRefGoogle Scholar
  17. 17.
    Li B, Acton ST (2007) Active contour external force using vector field convolution for image segmentation. IEEE Trans Image Process 16(8):2096–2106MathSciNetCrossRefGoogle Scholar
  18. 18.
    Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4): 321–331CrossRefGoogle Scholar
  19. 19.
    Xu C, Prince JL (2012) Active contours, deform- able models, and gradient vector flow. Online resource: In- cluding code download
  20. 20.
    Xu C, Yezzi A, Prince JL (2000) On the relationship between parametric and geometric active contours and its applications. In: 34th Asilomar conference on signals, systems and computers, vol 1, pp 483–489Google Scholar
  21. 21.
    Paragios N, Mellina-Gottardo O, Ramesh V (2004) Gradient vector flow fast geometric active contours. IEEE Trans Pattern Anal Mach Intell 26(3):402–407CrossRefGoogle Scholar
  22. 22.
    Goldenberg R, Kimmel R, Rivlin E, Rudzsky M (2001) Fast geodesic active contours. IEEE Trans Image Process 10(10):1467–1475MathSciNetCrossRefGoogle Scholar
  23. 23.
    Guilot L, Bergounioux M (2009) Existence and uniqueness results for the gradient vector flow and geodesic active contours mixed model. Commun Pure Appl Anal 8(4):1333–1349MathSciNetCrossRefGoogle Scholar
  24. 24.
    Li Q, Deng T, Xie W (2016) Active contours driven by divergence of gradient vector flow. Signal Process 120:185–199CrossRefGoogle Scholar
  25. 25.
    Rodtook A, Makhanov SS (2013) Multi-feature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer. J Vis Commun Image Represent 24(8):1414–1430CrossRefGoogle Scholar

Authors and Affiliations

  1. 1.Silicon Valley Future AcademyPalo AltoUSA
  2. 2.Electrical and Computer EngineeringJohns Hopkins UniversityBaltimoreUSA

Section editors and affiliations

  • Koichiro Deguchi
    • 1
  1. 1.Tohoku UniversitySendaiJapan