Pyramidal search of maximum coherence direction for biomedical image interpolation

Jingdan Zhang1, Yongmei Wang2, Baining Guo3
1Computer Science & Technology, Tsinghua University, Beijing, P. R. China
2Dept. of Information Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong, China
3Microsoft Research Asia, Beijing, P.R.China

Tóm tắt

A multiresolution technique for biomedical image interpolation is presented. It is an extension of the work on directional coherence interpolation (DCI) - a novel gray-level image interpolation method that interpolates the missing image data along the smoothed maximum coherence directions (MCDs). We propose to apply a pyramidal search strategy for MCD estimation. This coarse-to-fine scheme requires less computation time by starting with the reduced amount of data and propagating searching results to finer resolutions. In addition, it also improves robustness compared with our previous single resolution DCI.

Từ khóa

#Biomedical imaging #Interpolation #Image segmentation #Image resolution #Image analysis #Image texture analysis #Pixel #Computational efficiency #Coherence #Biomedical engineering

Tài liệu tham khảo

rosenfeld, 1984, Multiresolution Image Processing, 10.1007/978-3-642-51590-3 10.1109/42.921475 10.1145/356625.356626 thevenaz, 2000, Optimization of mutual information for multiresolution image registration, IEEE Trans Image Processing, 9, 2083, 10.1109/83.887976 10.1109/CVPR.2000.854933 wang, 2001, 3D image interpolation based on directional coherence, IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, 195, 10.1109/MMBIA.2001.991734 10.1109/38.135915 10.1109/ICIP.1995.537718 mallat, 1989, A theory of multiresolution singla decomposition: the wavelet representation, IEEE Trans Pattern Anal and Machine Intell, 11, 674, 10.1109/34.192463 10.1109/42.816070 10.1109/42.52980 10.1109/42.811263 10.1109/42.544506 10.1145/245.247 robb, 2000, Biomedical Imaging Visualization and Analysis