Robust Deformable Models for 2D and 3D Shape Estimation

Deformable models are useful tools to extract shape information from images and video sequences. However, the model has to be initialized in the vicinity of the object boundary, in order to foster convergence towards the desired features. This chapter describes four methods which alleviate this restriction. Despite their differences, they share three common features: (i) they use middle level features (edge segments) instead of low level ones; (ii) they explicitly assume that the measured features contain outliers and assign confidence degrees to the detected features and (iii) they adopt robust model updates, taking the confidence degrees into account. These four methods are reviewed and their performance is illustrated with selected examples.

[1]  Jamshid Dehmeshki,et al.  Medical Image Segmentation Using Deformable Models and Local Fitting Binary , 2011 .

[2]  Xun Wang,et al.  A comparative study of deformable contour methods on medical image segmentation , 2008, Image Vis. Comput..

[3]  Dimitris N. Metaxas,et al.  Deformable model-based face shape and motion estimation , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[4]  Q. Henry Wu,et al.  Leave one support vector out cross validation for fast estimation of generalization errors , 2004, Pattern Recognit..

[5]  Hervé Delingette,et al.  General Object Reconstruction Based on Simplex Meshes , 1999, International Journal of Computer Vision.

[6]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[7]  Torre Norte,et al.  Improving the robustness of parametric shape tracking with switched multiple models , 2002 .

[8]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

[9]  Scott T. Acton,et al.  Motion gradient vector flow: an external force for tracking rolling leukocytes with shape and size constrained active contours , 2004, IEEE Transactions on Medical Imaging.

[10]  Jorge S. Marques,et al.  Optimal and suboptimal shape tracking based on multiple switched dynamic models , 2001, Image Vis. Comput..

[11]  Gilles Celeux,et al.  Learning switching dynamic models for objects tracking , 2004, Pattern Recognit..

[12]  Laurent D. Cohen,et al.  Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[14]  Jorge S. Marques,et al.  Adaptive snakes using the EM algorithm , 2005, IEEE Transactions on Image Processing.

[15]  Junji Maeda,et al.  Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images , 2009, IEEE Journal of Selected Topics in Signal Processing.

[16]  Y. Bar-Shalom,et al.  The probabilistic data association filter , 2009, IEEE Control Systems.

[17]  Anil K. Jain,et al.  Deformable template models: A review , 1998, Signal Process..

[18]  J.S. Marques,et al.  Robust shape tracking in the presence of cluttered background , 2004, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[19]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[20]  Francesc Moreno-Noguer,et al.  Integration of deformable contours and a multiple hypotheses Fisher color model for robust tracking in varying illuminant environments , 2007, Image Vis. Comput..

[21]  Y. Bar-Shalom Tracking and data association , 1988 .

[22]  Junaed Sattar Snakes , Shapes and Gradient Vector Flow , 2022 .

[23]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[24]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .