WaterBalloons: A Hybrid Watershed Balloon Snake Segmentation

Dagher, Issam; Tom, K. El

doi:10.1109/ijcnn.2007.4370921

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally other segmentation methods (apart from region growing) may be adapted for watershed merging. An example of such a method is optimal thresholding [19] and active contours (snakes) [20,21]. In the latter approach selected watershed lines merely serve as contours that initialize a snake's evolution.…”

Section: Review Of Over-segmentation Methodsmentioning

confidence: 99%

Algorithm for selecting optimal clustering parameters used for over-segmentation reduction

Smółka

Skublewska‐Paszkowska

Lukasik

2016

ELECTROTECHNICAL REVIEW

View full text Add to dashboard Cite

The authors proposed a solution to the over-segmentation of color images processed by watershed segmentation algorithm. The solution utilizes hierarchical cluster analysis and treats watersheds as objects characterized by a number of attributes. This paper briefly discusses the solution (clustering methods, their parameters, selected watershed attributes) and presents an algorithm used for selecting optimal parameters for cluster analysis. Detailed results obtained for a set of test images are presented and discussed. Streszczenie. Autorzy zaproponowali rozwiązanie problem nadsegmentacji obrazów barwnych. Zjawisko to występuje w wyniku zastosowania transformacji wododziałowej. Rozwiązanie wykorzystuje hierarchiczną analizę skupień i traktuje zlewiska jako obiekty opisane zestawami atrybutów. Artykuł, krótko omawia zaproponowaną metodę (metody analizy skupień, jej parametry, wybrane atrybuty zlewisk) a także przedstawia algorytm zastosowany do doboru optymalnych parametrów analizy skupień. Artykuł przedstawia i omawia również wyniki otrzymane dla obrazów testowych. (Algorytm doboru optymalnych parametrów analizy skupień zastosowanej do redukcji nadsegmentacji).

show abstract

Section: Review Of Over-segmentation Methodsmentioning

confidence: 99%

Algorithm for selecting optimal clustering parameters used for over-segmentation reduction

Smółka

Skublewska‐Paszkowska

Lukasik

2016

ELECTROTECHNICAL REVIEW

View full text Add to dashboard Cite

show abstract

“…Xu and Prince () introduced a gradient vector flow (GVF) as a new external force field; this created spatial diffusion of the gradient vectors of a grey level or binary edge map derived from the image, thus spreading the effect of edges into homogenous regions. Dagher and El Tom () presented a water balloon snake model. Their method applied watershed segmentation to the detection of object locations.…”

Section: Active Contour Models and Snakesmentioning

confidence: 99%

Automatic reconstruction of regular buildings using a shape‐based balloon snake model

Yari

Mokhtarzade

Ebadi

et al. 2014

The Photogrammetric Record

View full text Add to dashboard Cite

Buildings are regarded as the most prominent man-made objects: hence, their automatic extraction from aerial and satellite images has attracted the interest of photogrammetric research communities. In this paper, a balloon snake, a wellknown active contour model, was developed for the precise extraction of building boundaries. Traditional active contours are highly sensitive to image data and are problematic when building boundaries are weakened, usually due to occlusions. To improve the efficiency of the traditional balloon snake model, a shape-based balloon snake model was introduced where knowledge about the expected geometrical shape of buildings was modelled and applied to the traditional snake representation. Implementation of the proposed algorithm confirmed its efficiency in the precise extraction of building boundaries. Experimental results and the qualitative and quantitative evaluations demonstrate the potential of the proposed shape-based balloon snake model and its superiority over traditional models.

show abstract

“…For example, in [22], Zhu et al propose gradient and direction vector flow (G&DVF) snake model. WaterBalloons [41] is introduced by I. Dagher et al The modified model combines both watershed segmentation and the balloon snake model, it provide the advantage of reducing watershed over-segmentation problems while preventing under-segmentation and ensure automatic initialization of traditional snake. F. Y. Shih et al present an improved snake model [44] associated with new regional similarity energy and a gravitation force field for complex shape image segmentation.…”

Section: Image Segmentationmentioning

confidence: 99%

Review of Parametric Active Contour Models in Image Processing

Guo¹,

Wang²,

Ma³

et al. 2013

JCIT

View full text Add to dashboard Cite

The parametric active contour models are widely used in computer vision and image processing. This paper reviews the research status of parametric active contour models in the past decade. The parametric active contour models have gained wide attention for a long time. First, the traditional snake and some typical modified models are introduced. Second, the parametric active contour models applications in the field of image processing are reviewed. Finally, the future work of parametric active contour models is pointed out.

show abstract

WaterBalloons: A Hybrid Watershed Balloon Snake Segmentation

Cited by 3 publications

References 11 publications

Algorithm for selecting optimal clustering parameters used for over-segmentation reduction

Algorithm for selecting optimal clustering parameters used for over-segmentation reduction

Automatic reconstruction of regular buildings using a shape‐based balloon snake model

Review of Parametric Active Contour Models in Image Processing

Contact Info

Product

Resources

About