The NURBS book
Wavelet-Based Affine Invariant Representation: A Tool for Recognizing Planar Objects in 3D Space
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hidden Markov models vs. syntactic modeling in object recognition
ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Dynamic B-snake model for complex objects segmentation
Image and Vision Computing
Affine-invariant B-spline moments for curve matching
IEEE Transactions on Image Processing
B-spline snakes: a flexible tool for parametric contour detection
IEEE Transactions on Image Processing
Active Contour External Force Using Vector Field Convolution for Image Segmentation
IEEE Transactions on Image Processing
Hi-index | 0.01 |
We propose a new adaptive B-spline VFC Snake model for object contour extraction. Bing Li et al. proposed vector field convolution (VFC) snake which has the advantages of superior noise robustness, reducing computational cost, and large capture range. However, it suffers from slow convergence speed due to large number of control points, as well as from difficulties in determining the weight factors associated to the internal energies constraining the smoothness of the curve. There is also no relevant criterion to determine the number of control points in VFC snake method. Our alternative approach expresses the curve as a non-uniform B-spline, in which fewer parameters are required and most importantly, internal energy calculation is eliminated because the smoothness is implicitly built into the model. A novel formulation of control points' movement estimation was established based on the least square fitting of non-uniform B-spline curve and VFC external force for the snake evolution process. A novel strategy of adding control points quickly matches the snake to desired complex shapes. Experimental results demonstrate the capability of adaptive shape description with high convergence speed of the proposed model.