Levelset and B-Spline Deformable Model Techniques for Image Segmentation: A Pragmatic Comparative Study

Deformable contours are now widely used in image segmentation, using different models, criteria and numeric schemes. Some theoretical comparisons between few deformable model methods have been published [1]. Yet, very few experimental comparative study on real data have been reported. In this paper, we compare a levelset with a B-spline based deformable model approach to understand the mechanisms involved in these widely spread methods and to compare both evolution and results on different kind of image segmentation problems. In general, both methods yield to similar results. However, specific differences appear when considering particular problems. 1 Motivations To model objects and segment images, both explicit [7, 18] and implicit [13, 2] deformable models have been proposed in the literature [12]. Among these methods, some focus on detecting edges characterized by high variation of features [10, 3], other on detecting regions characterized by homogeneity of spatially localized...

• Type: Conference
• Year: 2005
• Where: SCIA
• Authors: Diane Lingrand, Johan Montagnat
• Keywords: Deformable Model, Deformable Model Methods, Image Segmentation, SCIA 2005