Journal article Closed Access

Variational segmentation of vector-valued images with gradient vector flow.

Jaouen, Vincent; González, Paulo; Stute, Simon; Guilloteau, Denis; Chalon, Sylvie; Buvat, Irène; Tauber, Clovis


Citation Style Language JSON Export

{
  "DOI": "10.1109/TIP.2014.2353854", 
  "container_title": "IEEE Trans Image Process", 
  "title": "Variational segmentation of vector-valued images with gradient vector flow.", 
  "issued": {
    "date-parts": [
      [
        2014, 
        9, 
        4
      ]
    ]
  }, 
  "abstract": "<p>In this paper, we extend the gradient vector flow</p>\n\n<p>field for robust variational segmentation of vector-valued images.</p>\n\n<p>Rather than using scalar edge information, we define a vectorial</p>\n\n<p>edge map derived from a weighted local structure tensor of</p>\n\n<p>the image that enables the diffusion of the gradient vectors in</p>\n\n<p>accurate directions through the 4D gradient vector flow equation.</p>\n\n<p>To reduce the contribution of noise in the structure tensor,</p>\n\n<p>image channels are weighted according to a blind estimator of</p>\n\n<p>contrast. The method is applied to biological volume delineation</p>\n\n<p>in dynamic PET imaging, and validated on realistic Monte Carlo</p>\n\n<p>simulations of numerical phantoms as well as on real images.</p>", 
  "author": [
    {
      "given": "Vincent", 
      "family": "Jaouen"
    }, 
    {
      "given": "Paulo", 
      "family": "Gonz\u00e1lez"
    }, 
    {
      "given": "Simon", 
      "family": "Stute"
    }, 
    {
      "given": "Denis", 
      "family": "Guilloteau"
    }, 
    {
      "given": "Sylvie", 
      "family": "Chalon"
    }, 
    {
      "given": "Ir\u00e8ne", 
      "family": "Buvat"
    }, 
    {
      "given": "Clovis", 
      "family": "Tauber"
    }
  ], 
  "page": "4773-85", 
  "volume": "23", 
  "type": "article-journal", 
  "issue": "11", 
  "id": "16053"
}
40
0
views
downloads
Views 40
Downloads 0
Data volume 0 Bytes
Unique views 38
Unique downloads 0

Share

Cite as