Parametric active membrane for segmentation of multiple objects in an image

Das, Susmita; Mukherjee, Dipti Prasad

doi:10.1016/j.patcog.2010.08.024

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other less usual parameters, as appearing in Eqs. (9) to (11) are given the following values: D = 0.25, k p1 = 0.015, k p2 = 0.08, G = 5, and k g0 = 0.…”

Section: Object Segmentation Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Improving parametric active contours by using attracting point distance map

Marouf

Houacine

2016

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, we propose an improvement of the classical parametric active contours. The method, presented here, consists in adding a new energy term based on attraction point distance map chosen on the object. This additional term acts as attraction forces that constrain the contour to remain in the vicinity of the object. The distance map introduced here differs from the classical one since it is not based on the whole binary image, but rather constitutes a simplified and very fast version that relates only to one point. The additional forces, so introduced, act as a kind of balloon method. The attracting point is selected on an image based the shape of the object of interest. To improve convergence, we also propose the use of weighting factors for the externals forces as dependent on snake points. The method is evaluated for object segmentation in images, and is also tested for multi-object segmentation. Compared to the conventional balloon method, the presented approach admits a faster convergence and provides better results in particular at object concavities.

show abstract

“…The other less usual parameters, as appearing in Eqs. (9) to (11) are given the following values: D = 0.25, k p1 = 0.015, k p2 = 0.08, G = 5, and k g0 = 0.…”

Section: Object Segmentation Performance Evaluationmentioning

confidence: 99%

“…This exigency favours selection of fast methods like the parametric snakes [5,19]. This aspect is even more valuable for multi-object segmentation [9].…”

mentioning

confidence: 99%