Prior shape models for boundary finding
Tóm tắt
Prior shape information has proven to be a key component of modeling for boundary finding when the target objects belong to a class of similar shapes. Prior shape provides specific constraining information needed in order to overcome noise, missing boundaries and confusing image information. While a number of different methods have been proposed for incorporating prior information, the most natural approaches use a Bayesian formulation where prior information and image derived information are combined by optimizing a posterior probability. Shape parameters derived from the statistical variation of the boundary in a training set can be used to model the object. Generic information such as from a smoothness constraint can be incorporated into the framework when additional flexibility is needed due to a small available training set.
Từ khóa
#Probability #Bayesian methods #Optimization methods #Biomedical imaging #Shape measurement #Active shape model #Radiology #Noise shaping #Medical diagnostic imaging #Search methodsTài liệu tham khảo
10.1109/ICCV.1995.466854
10.1109/MMBIA.2000.852354
10.1109/CVPR.1989.37834
10.1109/34.166621
10.1007/BFb0013779
10.1109/34.865192
10.5244/C.8.3
10.1016/0262-8856(95)99727-I
rosenfeld, 1982, Digital Picture Processing
zeng, 1999, Segmentation and measurement of the cortex from 3D MR images using coupled surfaces propagation, IEEE Trans Med Imaging, 18
10.1007/BF00133570
10.1109/TC.1978.1674971
10.1016/0031-3203(81)90009-1
10.1109/CVPR.1989.37836
10.1016/0031-3203(73)90043-5
10.1145/362588.362594
10.1145/359997.360004
chow, 1989, Hands: A pattern theoretic study of biological shapes, Tech Rep Div Appl Math