A Novel GVF-Based Adaptive Extracting Formulation for Image Reconstruction
Bin Zhao, Qin Liang Li, Yingchun Wang, Guo Xing Jiang · Applied Mechanics and Materials · 2012
This paper proposed a fast boundary reconstruction algorithm based on adaptive gradient vector flow (GVF) deformable model. The novel dynamic GVF field performs faster and wider capture range over original GVF model, which efficiently attracts the model approaching the object contour more quickly and more stably. Based on the approximation error analysis the algorithm can automatically add new knots in contour curve, which makes the accelerated model achieve adaptive adjustment according to local characteristics of the boundary. The improved algorithm can greatly increase the reconstruction accuracy without compromising approximation efficiency. Additional experiments demonstrate the efficient procedure and fine performance of the approach.