Probabilistic contour extraction based on shape prior model

Abstract

Statistical shape prior model is employed to construct the dynamics in probablllstic contour estimation. By applying principal component analysis, plausible shape samples are efficiently generated to predict contour samples. Based on the shape-dependent dynamics and probabilistic image model, a particle filter is used to estimate the contour with a specific shape. Compared with the deterministic approach with shape information, the proposed method is simple yet more effective in extracting contours from images with shape variations and occlusion.

References

[1] PérezP., BlakeA., GangnetM.. Proc. of Int. Conf. On Computer Vision, 2001, II: 524-524

[2] CremersD., TischhauserF., WeickertJ., SchnorrC.. Int. J. of Computer Vision, 2002, 50: 295-295

[3] CootesT. F., TaylorC. J., CooperD. H., GrahamJ.. Computer Vision and Image Understanding, 1995, 61: 38-38

[4] GemanD., JedynakB.. IEEE Trans. Pattern Analysis and Machine Intelligence, 1996, 18: 1-1

[5] ArulampalamS., MaskellS., GordonN., ClappT.. IEEE Trans. Signal Processing, 2002, 5: 174-174